speech-to-text
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the ElevenLabs CLI using a shell script hosted on the official vendor GitHub repository (github.com/elevenlabs/cli).
- [COMMAND_EXECUTION]: The documentation suggests using npx to download and execute the vendor's command-line interface for project initialization.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted audio and video content. 1. Ingestion points: local audio/video files and remote URLs (YouTube, TikTok, etc.) processed in SKILL.md and references/transcription-options.md. 2. Boundary markers: No explicit prompt delimiters or warnings are provided in the instructions for the transcribed output. 3. Capability inventory: The skill performs network operations to ElevenLabs APIs and provides text output to the agent as shown in the Python and JavaScript examples in SKILL.md. 4. Sanitization: No evidence of text sanitization or filtering for the transcribed output.
Audit Metadata