Caveat verdict
gh-skillscan
Local security scanner skill that POSTs SKILL.md content to a localhost fastapi server it runs itself; no external exfiltration, curl commands target localhost:8001, and the skill's purpose is explicitly security review.
⚠ 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
network_out
Findings (5)
Accesses sensitive system files
SKILL.md · prose · downgraded · /etc/shadow
Pipe to bash — executes piped content as shell commands
skillscan/detectors.py · prose · downgraded · |bash
Pipe to sh — executes piped content as shell commands
skillscan/detectors.py · prose · downgraded · |sh
Bash /dev/tcp — raw TCP connection via shell
skillscan/detectors.py · prose · downgraded · /dev/tcp/
Accesses .ssh directory
SKILL.md · prose · downgraded · .ssh/
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary.
network_out Is this flag fair?
Thanks — recorded.