sound-effects
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses official SDKs (elevenlabs for Python and @elevenlabs/elevenlabs-js for Node.js) to interact with ElevenLabs services.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-defined text to generate audio, representing an attack surface for indirect prompt injection. 1. Ingestion points: The 'text' parameter in the convert method within SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Network access to api.elevenlabs.io and file writing to the local filesystem (e.g., thunder.mp3) in SKILL.md. 4. Sanitization: None.
Audit Metadata