add-voice-transcription
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill downloads and transcribes WhatsApp voice notes (user-generated content) — see downloadMediaMessage and transcribeWithOpenAI in src/transcription.ts and the transcription integration in src/index.ts — so the agent ingests arbitrary third‑party user content from group chats as runtime context.
Audit Metadata