ClawAudit verdict
feishu-multi-agent
feishu-multi-agent-replay
The skill appears to be a multi-agent relay for Feishu group chats. While it seems to be designed for legitimate purposes, it involves executing scripts and interacting with the file system, which could be risky if not used properly.
⚠ 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 (2)
HTTP request to bare IP address — common in malicious payloads
config/relay-config.json · prose · downgraded · http://127.0.0.1
Python urllib.request — network access
scripts/feishu_multi_agent.py · prose · downgraded · urllib.request
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.