ClawAudit verdict
booking-skill
korean-booking
While the skill seems legitimate, the interaction with an external API and storage of user data could pose risks.
⚠ 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.
Findings (4)
References child_process — can spawn system processes
api/browser/open-url.js · prose · downgraded · child_process
Uses exec() — may execute shell commands
docs/IMPLEMENTATION-SUMMARY.md · prose · downgraded · exec(
Node http/https module — low-level network access
api/skill.js · prose · downgraded · require('https')
References agent memory files
docs/IMPLEMENTATION-SUMMARY.md · prose · downgraded · MEMORY.md
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.
Is this flag fair?
Thanks — recorded.