ClawAudit verdict
code-inspector
Installs a Python package from a public repo and scans code locally; there is no evidence of malicious exfiltration or execution.
⚠ 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 (4)
Uses eval() — can execute arbitrary code
SKILL.md · prose · downgraded · eval(
Possible hardcoded credential
SKILL.md · prose · downgraded · api_key = "sk-abc123
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
Popular HTTP library — network access
code_inspector/detectors.py · prose · downgraded · axios
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.