Bawwab: Top 302 scan

planning-with-files

Not malicious, needs a look Reviewed: expected behaviour

Bawwab's static rules found patterns that deserve a human look. This is not a finding that the package is malicious; the review notes below say what each pattern turned out to be.

Why it was flagged

The static rules marked this “Not malicious, needs a look” because of:

Kind
Plugin
Source
github
Repository
OthmanAdi/planning-with-files
Commit
51bf62def62d1cb317d37936929b4ef97cf862c3
Listed in
OthmanAdi/planning-with-files
Popularity
28,153 GitHub stars (2026-11-20)
Link
https://github.com/OthmanAdi/planning-with-files/tree/51bf62def62d1cb317d37936929b4ef97cf862c3
Scanned
2026-11-20T23:10:51+00:00
Scan time
54.2 s
Scanned as
plugin
Review note: Flags are copies of a documented local session-catchup script, test env copies and the plugin's own lifecycle hooks; nothing malicious.

Findings (23)

credential-access: Touches credentials or secrets high

.agents/skills/planning-with-files/scripts/session-catchup.py:151

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

.codebuddy/skills/planning-with-files/scripts/session-catchup.py:151

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

.codex/skills/planning-with-files/scripts/session-catchup.py:151

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

.continue/skills/planning-with-files/scripts/session-catchup.py:151

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

.cursor/skills/planning-with-files/scripts/session-catchup.py:151

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

.factory/skills/planning-with-files/scripts/session-catchup.py:151

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

.gemini/skills/planning-with-files/scripts/session-catchup.py:151

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

.hermes/skills/planning-with-files/scripts/session-catchup.py:78

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

"""Spell a project path the way Claude Code names ~/.claude/projects entries.

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

.mastracode/skills/planning-with-files/scripts/session-catchup.py:51

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

"""Spell a project path the way Claude Code names ~/.claude/projects entries.

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

.opencode/skills/planning-with-files/scripts/session-catchup.py:127

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

.pi/skills/planning-with-files/scripts/session-catchup.py:151

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

scripts/session-catchup.py:84

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

"""Spell a project path the way Claude Code names ~/.claude/projects entries.

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

skills/i18n/planning-with-files-ar/scripts/session-catchup.py:148

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

skills/i18n/planning-with-files-de/scripts/session-catchup.py:149

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

skills/i18n/planning-with-files-es/scripts/session-catchup.py:152

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

skills/i18n/planning-with-files-zh/scripts/session-catchup.py:150

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

skills/i18n/planning-with-files-zht/scripts/session-catchup.py:149

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

skills/planning-with-files/scripts/session-catchup.py:151

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

paths when it names ~/.claude/projects/ entries. Earlier versions of

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Expected for what this tool does

The session-catchup script can read Claude Code transcripts under ~/.claude/projects to recover context lost since the last planning-file update. Its docstring says automatic callers use no-history mode and transcript excerpts need an explicit request. Output goes to the local terminal; the script makes no network calls.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

tests/test_bsd_userland_sim.py:204

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

exfil.combo: Reads credentials and makes network calls med

tests/test_hermes_session_binding.py:83

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0037 Data from Local SystemMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0025 Exfiltration via Cyber Means

before = dict(os.environ)

What this means: Credential access together with outbound requests in one file is the shape of data theft.

The rule's general advice: Do not install unless the flow is understood and benign. (see the review note for this case)

Known false alarm

A test saves and restores os.environ around a session-binding check. Nothing is sent anywhere.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets high

tests/test_inject_plan_python_parity.py:630

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

self.env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

plugin.hook-broad: Plugin hook runs on every tool call med

.codex/hooks.json:45

MITRE ATLAS AML.T0142 Event Triggered Execution

python3 .codex/hooks/permission_request.py 2>/dev/null || python3 "$HOME/.codex/hooks/permission_request.py" 2>/dev/null || true

What this means: A hook with no specific matcher runs a command each time the assistant uses any tool, giving it constant access to your session.

The rule's general advice: Check the hook command, and prefer plugins whose hooks match specific tools. (see the review note for this case)

Expected for what this tool does

The Codex PermissionRequest hook runs the plugin's own permission_request.py, which only prints a reminder to review task_plan.md. It never blocks or approves the request.

Reviewed by Claude (AI-assisted review), 2026-11-21

plugin.hook-broad: Plugin hook runs on every tool call med

hooks/hooks.json:10

MITRE ATLAS AML.T0142 Event Triggered Execution

sh

What this means: A hook with no specific matcher runs a command each time the assistant uses any tool, giving it constant access to your session.

The rule's general advice: Check the hook command, and prefer plugins whose hooks match specific tools. (see the review note for this case)

Expected for what this tool does

The plugin's lifecycle hooks run its own hooks/claude-hook.sh through 'sh' to restore and check planning context. This is the plugin's stated purpose.

Reviewed by Claude (AI-assisted review), 2026-11-21

78 low-severity notes (informational, do not affect the result)

files.binary-unscanned: Binary files not analysed low

4 binary files not analysed; use --deep to run in the sandbox

What this means: Prebuilt executables cannot be read by static rules, so what they do is unknown until they run.

What you can do: Use --deep to run the package in the sandbox, or prefer packages built from source.

install-dir-access: Reads or writes Claude's install folders low

.gitignore:31

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

.claude/

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.agents/skills/planning-with-files/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.agents/skills/planning-with-files/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.codebuddy/skills/planning-with-files/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.codebuddy/skills/planning-with-files/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

credential-access: Touches credentials or secrets low

.codex/hooks/codex_hook_adapter.py:348

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

What you can do: Confirm the tool needs this; otherwise do not install.

install-dir-access: Reads or writes Claude's install folders low

.codex/skills/planning-with-files/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.codex/skills/planning-with-files/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.continue/skills/planning-with-files/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.cursor/skills/planning-with-files/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.cursor/skills/planning-with-files/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.dsh/packages/dsh-planning-with-files/src/core.ts:685

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

path.join(root, ".claude", "skills"),

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.factory/skills/planning-with-files/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.factory/skills/planning-with-files/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.gemini/skills/planning-with-files/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

credential-access: Touches credentials or secrets low

.hermes/plugins/planning-with-files/shell_hook.py:70

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = dict(os.environ)

What this means: Reads files or environment holding keys, tokens or sessions.

What you can do: Confirm the tool needs this; otherwise do not install.

install-dir-access: Reads or writes Claude's install folders low

.hermes/plugins/planning-with-files/shell_hook.py:42

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

home / ".claude" / "skills" / "planning-with-files" / "scripts",

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.hermes/skills/planning-with-files/scripts/session-catchup.py:13

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

- Claude Code (.claude/projects/)

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.mastracode/skills/planning-with-files/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.opencode/packages/opencode-planning-with-files/src/core.ts:685

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

path.join(root, ".claude", "skills"),

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.opencode/skills/planning-with-files/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.pi/skills/planning-with-files/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

.pi/skills/planning-with-files/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

examples/boxlite/quickstart.py:28

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

skill_base = Path.home() / ".claude" / "skills" / "planning-with-files"

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

examples/file-only-recovery/grade.py:45

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

"/.claude/projects/",

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

scripts/_v240_update_hook_bodies.py:168

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

'KNOWN_PS1=$(ls \\"$HOME/.claude/skills/planning-with-files/scripts/check-complete.ps1\\" \\"$HOME/.claude/plugins/marketplaces/planning-with-files/scripts/check-complete.ps1\\" 2>/dev/null | head -1)

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

scripts/session-catchup.py:10

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

- Claude Code (.claude/projects/)

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

skills/i18n/planning-with-files-ar/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

skills/i18n/planning-with-files-ar/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

skills/i18n/planning-with-files-de/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

skills/i18n/planning-with-files-de/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

skills/i18n/planning-with-files-es/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

skills/i18n/planning-with-files-es/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

skills/i18n/planning-with-files-zh/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

skills/i18n/planning-with-files-zh/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

skills/i18n/planning-with-files-zht/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

skills/i18n/planning-with-files-zht/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

skills/planning-with-files/scripts/gate-stop.sh:25

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

TARGET=$(ls "${HOME}/.claude/skills/planning-with-files/scripts/check-complete.sh" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

skills/planning-with-files/scripts/plan-doctor.sh:159

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

".claude/skills/planning-with-files" \

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

credential-access: Touches credentials or secrets low

tests/test_catchup_cross_project_guard.py:3

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

Claude Code names ~/.claude/projects entries by folding every character

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_catchup_project_dir.py:4

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

in ~/.claude/projects/ names. The pre-v3.8.0 mapper replaced '_' with '-'

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_catchup_store_resolution_parity.py:17

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

Folding rules pinned here were measured against 24 real ~/.claude/projects

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_claude_plugin_operations.py:84

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

self.env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

install-dir-access: Reads or writes Claude's install folders low

tests/test_claude_plugin_operations.py:66

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

self.assertNotIn(".claude/plugins/marketplaces", serialized)

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

credential-access: Touches credentials or secrets low

tests/test_codex_hooks.py:166

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_codex_nested_root_isolation.py:73

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_containment.py:219

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_cursor_bash_named_plans.py:33

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_cursor_hook_schema.py:84

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_cursor_powershell_named_plans.py:39

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

install-dir-access: Reads or writes Claude's install folders low

tests/test_custom_adapter_catchup_privacy.py:441

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

for host_store in (".claude", ".codex", "opencode.db", "jsonl"):

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

credential-access: Touches credentials or secrets low

tests/test_gate.py:48

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

self.env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_hermes_first_class.py:541

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = {k: v for k, v in os.environ.items() if k not in ENV_KEYS}

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_hermes_session_binding.py:83

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

before = dict(os.environ)

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_hook_body_v240.py:712

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

self.env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

install-dir-access: Reads or writes Claude's install folders low

tests/test_hook_body_v240.py:92

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

"$HOME/.claude/skills/planning-with-files/scripts/skill-hook.sh",

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

credential-access: Touches credentials or secrets low

tests/test_hook_resolver_integration.py:24

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_injection_determinism.py:97

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_ledger.py:51

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

self.env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_ledger_utf8.py:86

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

self.env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_nested_plan_isolation.py:69

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

self.env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_phase_status_locking.py:31

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

self.env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

install-dir-access: Reads or writes Claude's install folders low

tests/test_plugin_skill_surface.py:13

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

`~/.claude/skills/planning-with-files-de/`.

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

credential-access: Touches credentials or secrets low

tests/test_powershell_literal_paths.py:39

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_precompact_hook.py:117

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

self.env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

install-dir-access: Reads or writes Claude's install folders low

tests/test_precompact_hook.py:76

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

"$HOME/.claude/skills/planning-with-files/scripts/skill-hook.sh", scalar

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

credential-access: Touches credentials or secrets low

tests/test_pretool_throttle.py:27

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_quiet_completion_hooks.py:26

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

key: value for key, value in os.environ.items()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

install-dir-access: Reads or writes Claude's install folders low

tests/test_script_location_parity.py:5

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

(``~/.claude/skills/planning-with-files/scripts``), and the plugin-marketplace

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

tests/test_session_catchup.py:466

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

self.claude_project_dir = self.root / ".claude" / "projects" / sanitized

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

credential-access: Touches credentials or secrets low

tests/test_session_plan_ambiguity.py:41

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

self.env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

credential-access: Touches credentials or secrets low

tests/test_session_start_python_isolation.py:28

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

install-dir-access: Reads or writes Claude's install folders low

tests/test_skill_hook_dispatch_parity.py:259

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

language variants install under $HOME/.claude/skills/<variant-name>. The

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

install-dir-access: Reads or writes Claude's install folders low

tests/test_stop_hook_dispatch.py:140

MITRE ATLAS AML.T0081 Modify AI Agent Configuration

self.assertIn(".claude/skills/planning-with-files", scalar)

What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.

What you can do: Check which files it adds there and that you want them.

credential-access: Touches credentials or secrets low

tests/test_unarmed_plan_ambiguity.py:24

OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration

self.env = os.environ.copy()

What this means: Reads files or environment holding keys, tokens or sessions.

The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)

Known false alarm

Tests copy os.environ to run the plugin's scripts in a subprocess. No credentials are read.

Reviewed by Claude (AI-assisted review), 2026-11-21

Dispute this result

Maintainer and think this is wrong? Open a dispute on GitHub with the target id plugin-othmanadi-planning-with-files-33a648.