ClawAudit verdict
命理大师
university-applications
Chinese fortune-telling skill with thorough security disclosures; data is stored locally only, network calls are opt-in and limited to specific LLM endpoints, no env vars are read, and the skill includes explicit user-controlled data deletion mechanisms.
⚠ 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)
Possible hardcoded credential
SKILL.md · frontmatter · credential: "user-provided LLM API key, entered at runtime, stored in browser lo
Popular HTTP library — network access
SKILL.md · frontmatter · axios
Instructs covert action — may act without user awareness
scripts/ziwei.js · prose · downgraded · silently
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.