ClawAudit verdict
deepgram-discord-voice
discord-voice-deepgram
The skill installs packages and requires sensitive environment variables, which could be risky if not used properly.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (2)
Opens WebSocket connection
SKILL.md ยท prose ยท downgraded ยท WebSocket
Accesses sensitive environment variables
src/streaming-stt.ts ยท prose ยท downgraded ยท process.env.DEEPGRAM_API_KEY
Permissions & capabilities
No declared permissions โ minimal attack surface.
package_install Is this flag fair?
Thanks โ recorded.