ClawAudit verdict
健康管理
jiankangguanli
The skill dynamically fetches an API key at runtime from an external URL (curl https://jiyinjia.jinbaisen.com/!token?key=skill_jk) and then sends user health data (including names, medical history, lab results) to a third-party LLM endpoint; this combines credential retrieval from an external server with transmission of sensitive personal health information to a non-user-controlled backend.
⚠ 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
credential_access
Findings (1)
subprocess execution — runs system commands from Python
scripts/health_assistant.py · prose · downgraded · subprocess.run(
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.
credential_access Is this flag fair?
Thanks — recorded.