ClawAudit verdict
skill-a-create-meeting
The skill orchestrates a complex workflow involving multiple tools and services (e.g., Gitea, Tencent Meeting). While it seems designed for legitimate meeting creation, its complexity and the potential for misuse or misconfiguration 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 (3)
HTTP request to bare IP address — common in malicious payloads
env-example.txt · prose · downgraded · http://43.156.243.152
References child_process — can spawn system processes
main.js · prose · downgraded · child_process
Python os.getenv — reads environment variable
scripts/create_meeting.py · prose · downgraded · os.getenv(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/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.