stt-integration
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: 0.80). The skill ingests arbitrary user-provided audio and transcription results (untrusted user-generated content) as part of its runtime workflow — e.g., the Next.js API route and processAudioUpload in examples/vercel-ai-stt/README.md and the transcribe-audio.sh / webhook handlers which accept uploads and consume webhook payloads containing transcription text — so the agent will read/interpret third-party content.
Audit Metadata