NYC

ASR

Warn

Audited by Snyk on Feb 15, 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 (via the Express endpoint /api/transcribe, CLI file/base64 inputs, and directory transcription scripts) and transcribes that untrusted, third-party content into text for further processing, which could contain indirect prompt-injection payloads.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:16 PM