NYC

sound-effects

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Data Exposure & Exfiltration] (SAFE): The skill handles the API key via environment variables. Network calls are made to the legitimate ElevenLabs API (api.elevenlabs.io).
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): Uses official libraries: 'elevenlabs' (Python) and '@elevenlabs/elevenlabs-js' (Node.js).
  • [Indirect Prompt Injection] (LOW): Ingests user-provided text for audio generation. 1. Ingestion point: 'text' parameter in SKILL.md. 2. Boundary markers: Absent. 3. Capability: Network API calls (elevenlabs.io). 4. Sanitization: Absent. Low risk as output is audio.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:37 PM