ClawAudit verdict
wyze-sensors
The skill appears to be a simple Wyze sensor reader with no suspicious capabilities or behaviors.
⚠ 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)
Instruction-prose smuggling shape detected: collects a sensitive target ("password") and emits it outward ("report"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.
SKILL.md · Read Wyze **sensor** states through the bundled `sensors` CLI, which wraps [`wyze-node`](https://www.npmjs.com/package/wyze-node). Reuses the same cached login
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.