Caveat verdict
qinglong
qinglong-skills
This is another QingLong panel management skill that explicitly states it only communicates with the user's self-hosted panel; the script-based approach using curl/jq is transparent and confined to the user's own infrastructure.
⚠ 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.
Findings (8)
Possible hardcoded credential
README_zh-CN.md · code · SECRET="你的Client Secret
Accesses shell history/config
README_zh-CN.md · code · ~/.zshrc
Pipe to python — executes piped content as Python code
references/api.md · prose · downgraded · | python3
Popular HTTP library — network access
SKILL.md · code · axios
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
HTTP request to bare IP address — common in malicious payloads
README_zh-CN.md · prose · downgraded · http://192.168.1.100
Accesses OpenClaw config/secrets directly
README_zh-CN.md · prose · downgraded · ~/.openclaw/openclaw.json
References agent configuration files
README_zh-CN.md · prose · downgraded · CLAUDE.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 3 environment variables. (1 sensitive: QINGLONG_CLIENT_SECRET). Requires 2 system binaries. (1 elevated: curl).
Is this flag fair?
Thanks — recorded.