Caveat verdict
eat-skill
Reads a user profile and optionally calls a map API with a provided key; all actions are legitimate for its purpose.
⚠ 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
credential_access
Findings (4)
Popular HTTP library — network access
vendor/amap-lbs-skill/SKILL.md · frontmatter · axios
References child_process — can spawn system processes
vendor/amap-lbs-skill/scripts/route-planning.js · prose · downgraded · child_process
Uses exec() — may execute shell commands
vendor/amap-lbs-skill/scripts/route-planning.js · prose · downgraded · exec(
Accesses sensitive environment variables
vendor/amap-lbs-skill/index.js · prose · downgraded · process.env.AMAP_KEY
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.
credential_access Is this flag fair?
Thanks — recorded.