ClawAudit verdict
lingxi-watchlist-skill
Collects device MAC addresses for 'risk control' binding (up to 5 devices per user) and stores auth tokens in a shared directory; device fingerprinting beyond what's needed for a stock watchlist skill is an unusual data collection practice.
⚠ 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 (1)
Node http/https module — low-level network access
skill-entry.js · prose · downgraded · require("http")
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.