ClawAudit verdict
code-reviewer
cuihua-code-reviewer
An AI-powered code review assistant for OpenClaw developers that uses git to analyze code quality, security vulnerabilities, and performance issues; credential_access is not actively used (the metadata lists no required env vars), and all behavior matches local code analysis.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
credential_access
Findings (6)
Uses eval() — can execute arbitrary code
EXAMPLES.md · code · eval(
Possible hardcoded credential
code-review-report.md · code · API_KEY = "sk-1234567890abcdef1234567890abcdef
Uses exec() — may execute shell commands
code-review-report.md · code · exec(
References child_process — can spawn system processes
analyzer.js · prose · downgraded · child_process
References webhook/callback URL
EXAMPLES.md · code · WEBHOOK_URL
Node http/https module — low-level network access
EXAMPLES.md · code · require('https')
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary. (1 elevated: git).
credential_access Is this flag fair?
Thanks — recorded.