chisle
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:
credential-access: Touches credentials or secrets (high, 10× · first at .gitignore:4)remote-code.pipe-shell: Pipes a download into a shell (high, 2× · first at install.sh:2)
- Kind
- Plugin
- Source
- github
- Repository
- JayPokale/Chisle
- Commit
b0fde39bbc2901683d27114071b5954c2799430a- Listed in
- davepoon/buildwithclaude
- Popularity
- 1,228 GitHub stars (2026-11-20)
- Link
- https://github.com/JayPokale/Chisle/tree/b0fde39bbc2901683d27114071b5954c2799430a
- Scanned
- 2026-11-20T23:21:00+00:00
- Scan time
- 15.5 s
- Scanned as
- plugin
Review note: Benchmark scripts copy the developer's Claude login into a temporary config folder to run tests; the rest is docs, tests and an output-compression hook, with nothing malicious.
Findings (13)
credential-access: Touches credentials or secrets high
.gitignore: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
.env.local
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
.env.local is listed in .gitignore so it is not committed. Nothing is read.
Reviewed by Claude (AI-assisted review), 2026-11-21
remote-code.pipe-shell: Pipes a download into a shell high
install.sh:2
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
# chisle — curl|bash shim. Delegates to the Node installer via npx.
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 comment in install.sh describing the curl | bash install method. The script itself runs the project's own Node installer (local bin/install.js or npx github:JayPokale/Chisle).
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
benchmarks/run-live.sh:42
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
cp "$HOME/.claude/.credentials.json" "$ISO/" 2>/dev/null || { echo "no Claude credentials found"; exit 1; }
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
A developer benchmark script copies ~/.claude/.credentials.json (or Pi's auth.json) into a fresh temporary config folder so it can run claude without the user's settings or plugins, and deletes the folder on exit. It sends nothing elsewhere and the plugin never runs it.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
benchmarks/agentic/run.js:40
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
fs.copyFileSync(path.join(os.homedir(), '.claude', '.credentials.json'), path.join(ISO, '.credentials.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)
Expected for what this tool does
Benchmark runners copy ~/.claude/.credentials.json into a temporary isolated config folder (removed on exit) so the claude CLI can run benchmark arms cleanly. They are developer tools, not run by the plugin, and they don't send the file anywhere.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
benchmarks/quality/run.js: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
fs.copyFileSync(path.join(os.homedir(), '.claude', '.credentials.json'), path.join(ISO, '.credentials.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)
Expected for what this tool does
Benchmark runners copy ~/.claude/.credentials.json into a temporary isolated config folder (removed on exit) so the claude CLI can run benchmark arms cleanly. They are developer tools, not run by the plugin, and they don't send the file anywhere.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
benchmarks/results/raw-backfires/run.js: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
fs.copyFileSync(path.join(os.homedir(), '.claude', '.credentials.json'), path.join(ISO, '.credentials.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)
Expected for what this tool does
Benchmark runners copy ~/.claude/.credentials.json into a temporary isolated config folder (removed on exit) so the claude CLI can run benchmark arms cleanly. They are developer tools, not run by the plugin, and they don't send the file anywhere.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
benchmarks/results/raw-prompt-compression/run.js: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
fs.copyFileSync(path.join(os.homedir(), '.claude', '.credentials.json'), path.join(ISO, '.credentials.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)
Expected for what this tool does
Benchmark runners copy ~/.claude/.credentials.json into a temporary isolated config folder (removed on exit) so the claude CLI can run benchmark arms cleanly. They are developer tools, not run by the plugin, and they don't send the file anywhere.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
benchmarks/results/raw-trim/run.js:12
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
fs.copyFileSync(path.join(os.homedir(), '.claude', '.credentials.json'), path.join(ISO, '.credentials.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)
Expected for what this tool does
Benchmark runners copy ~/.claude/.credentials.json into a temporary isolated config folder (removed on exit) so the claude CLI can run benchmark arms cleanly. They are developer tools, not run by the plugin, and they don't send the file anywhere.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
hooks/chisle-config.js:208
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
path.join(cwd, '.claude', 'settings.local.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
Reads only the outputStyle field from the project and user Claude settings files to detect the active output style. No secrets.
Reviewed by Claude (AI-assisted review), 2026-11-21
remote-code.pipe-shell: Pipes a download into a shell high
site/src/components/GetStarted.tsx:20
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
cmd: "curl -fsSL https://raw.githubusercontent.com/JayPokale/Chisle/main/install.sh | 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
The project website shows its own curl | bash install command as text. Nothing is run.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
tests/test_hooks.js:482
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
f.write('home/.claude/settings.json', { outputStyle: 'Explanatory' });
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
Unit tests write fake settings.json contents and hook commands into temporary folders. Test data only.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
tests/test_installer.js:199
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
{ hooks: [{ type: 'command', command: 'node ~/.claude/chisle-hooks/chisle-compress-output.js' }] },
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
Unit tests write fake settings.json contents and hook commands into temporary folders. Test data only.
Reviewed by Claude (AI-assisted review), 2026-11-21
plugin.hook-broad: Plugin hook runs on every tool call med
.claude-plugin/plugin.json:39
MITRE ATLAS AML.T0142 Event Triggered Execution
node "${CLAUDE_PLUGIN_ROOT}/hooks/chisle-compress-output.js"; exit 0
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
PostToolUse hook on Bash, Agent, WebFetch, WebSearch, Grep, Glob and MCP tools runs the plugin's local compressor to shorten very large tool output, which is the plugin's stated purpose. The script only uses fs, path and crypto, with no network access.
Reviewed by Claude (AI-assisted review), 2026-11-21
7 low-severity notes (informational, do not affect the result)
install-dir-access: Reads or writes Claude's install folders low
.gitignore:13
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
benchmarks/replay-compress.js:24
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
: path.join(process.env.CLAUDE_CONFIG_DIR || path.join(os.homedir(), '.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
benchmarks/agentic/run.js:47
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
const cache = path.join(os.homedir(), '.claude', 'plugins', 'cache', 'ponytail', 'ponytail');
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
bin/install.js:190
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
return path.join(os.homedir(), '.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
hooks/chisle-config.js:38
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
return process.env.CLAUDE_CONFIG_DIR || path.join(os.homedir(), '.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
hooks/chisle-statusline.ps1:6
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
$configDir = if ($env:CLAUDE_CONFIG_DIR) { $env:CLAUDE_CONFIG_DIR } else { Join-Path $HOME '.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
tests/test_hooks.js:461
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
fs.mkdirSync(path.join(root, 'proj', '.claude'), { recursive: true });
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-jaypokale-chisle-5cbe4a.