speech-to-text
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses official SDKs and endpoints for ElevenLabs services. It correctly identifies sensitive credentials (ELEVENLABS_API_KEY) and provides guidance on secure management using environment variables and single-use tokens for browser-based implementations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external audio/video data which constitutes an attack surface. However, the risk is negligible as the skill's primary function is data conversion (speech-to-text) and it does not possess exploitable capabilities like arbitrary command execution or write access to sensitive paths.
Audit Metadata