ClawAudit verdict
qinglong
qinglong-skill
This skill manages the user's own self-hosted QingLong panel via its REST API using credentials the user provides; all curl calls target user-specified local/self-hosted URLs and no data is sent to external third parties.
⚠ 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.
Permission integrity
network_out
Findings (3)
Pipe-to-python pattern — remote code execution risk
api-reference.md · code · curl -s "http://192.168.1.100:5700/api/user/login?client_id=xxx&client_secret=yy
Pipe to python — executes piped content as Python code
api-reference.md · code · | python3
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://192.168.1.100
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class C). 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.
network_outnetwork_in Is this flag fair?
Thanks — recorded.