ClawAudit verdict

虾BB

xiabb

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The skill provides a voice-to-text service for macOS and does not contain any malicious or deceptive behavior.

⚠ 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.

48
security
100
transparency
90
maintenance

Findings (5)

Pattern match high

Recursive delete from root or home — destructive command

uninstall.sh · prose · downgraded · rm -rf ~

Pattern match medium

Instructs covert action — may act without user awareness

content/video-script-youtube.md · prose · downgraded · silently

Pattern match medium

Opens WebSocket connection

README.md · code · WebSocket

Pattern match medium

Accesses system credential store

content/wechat-article.md · prose · downgraded · Keychain

Pattern match low

Popular HTTP library — network access

scripts/test-smart-modes.sh · prose · downgraded · got

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?

Check another skill Browse the registry Auditing your own skills or configs? Use the API