ClawAudit verdict
code-review-automation
The skill installs packages, which could potentially be used for malicious purposes, but there is no clear evidence.
⚠ 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
package_install
Findings (5)
Possible hardcoded credential
tests/test_security_scanner.py · prose · downgraded · api_key = "sk-1234567890abcdefghijklmnopqrstuv
subprocess execution — runs system commands from Python
code_review/security_scanner.py · prose · downgraded · subprocess.call(
os.system/popen — direct OS command execution
code_review/security_scanner.py · prose · downgraded · os.system(
subprocess with shell=True — command injection vector
tests/test_security_scanner.py · prose · downgraded · subprocess.call(user_input, shell=True
Python os.getenv — reads environment variable
code_review/claude_client.py · prose · downgraded · os.getenv(
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
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.