speech-to-text
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted audio and video content which could contain spoken instructions intended to manipulate the AI agent's behavior once the content is converted to text. * Ingestion points: Audio and video files processed in SKILL.md and references/transcription-options.md. * Boundary markers: There are no explicit markers or instructions provided to the agent to ignore or isolate the transcribed text from its own operating instructions. * Capability inventory: The skill performs network requests to the ElevenLabs API and reads local files. * Sanitization: The skill does not sanitize the resulting transcription before returning it to the agent context.
Audit Metadata