elevenlabs
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute a local script
tools/voiceover.pyto process scene narration and generate audio assets.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content fromVOICEOVER-SCRIPT.mdto guide the audio synthesis and scene timing generation workflow. - Ingestion points:
VOICEOVER-SCRIPT.mdis read to extract narration and scene structure. - Boundary markers: None specified to differentiate between data and instructions within the script file.
- Capability inventory: The agent has the ability to make external API calls to ElevenLabs and execute local Python scripts (
tools/voiceover.py). - Sanitization: No sanitization or validation of the markdown content is mentioned before it is used for audio generation.
Audit Metadata