Caveat verdict
skill-auditor-plus
Static analysis auditing for AgentSkills; purely analytical with no credential access or external network calls.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (5)
Pipe to python — executes piped content as Python code
SKILL.md · code · |
python3
Possible hardcoded credential
references/best-practices.md · code · api_key = "sk-1234567890
Python os.getenv — reads environment variable
references/best-practices.md · code · os.getenv(
Accesses .ssh directory
scripts/security_audit.py · prose · downgraded · .ssh/
Accesses cloud provider credentials
scripts/security_audit.py · prose · downgraded · ~/.aws
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.