ClawAudit verdict
openclaw-voice
The skill appears to be a legitimate voice conversation tool using Whisper STT and ElevenLabs TTS, with no evidence of malicious 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.
Findings (4)
References child_process — can spawn system processes
SKILL.md · prose · downgraded · child_process
Dynamic import() — loads module at runtime
src/backup.js · prose · downgraded · import('
Uses exec() — may execute shell commands
src/db.js · prose · downgraded · exec(
Opens WebSocket connection
VOICE_CALLING_SPEC.md · code · WebSocket
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.