media-audio-gen
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text and media files for audio generation and dubbing, creating a surface for potential instruction injection.
- Ingestion points: The skill ingests text, audio samples, and video files for processing as described in
SKILL.mdunder the TTS, Voice Cloning, and Dubbing workflows. - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between data to be processed and instructions embedded within that data.
- Capability inventory: The skill utilizes the ElevenLabs MCP server (
elevenlabs-mcp) to perform network-based media generation and translation. - Sanitization: The skill does not define methods for sanitizing or validating user input to prevent embedded instructions from influencing agent behavior during the generation process.
Audit Metadata