ClawAudit verdict
cybersecured-agent-risk-advisory
The skill installs a CLI tool to perform security scans and submit risk assessments for AI agents; credential_access is limited to reading an API key from the environment for authentication to the declared cybersecured-agent service, matching the legitimate risk-advisory purpose.
⚠ 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 (2)
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
HTTP request to bare IP address — common in malicious payloads
references/questionnaire-guide.md · prose · downgraded · http://100.100.100.200
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.