scenario-elevenlabs
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied data which could contain malicious instructions.
- Ingestion points: The skill ingests user-provided text for speech and music generation (
text,prompt) and processes uploaded audio or video assets for dubbing and voice transformation (file,audio) as described in SKILL.md. - Boundary markers: There are no instructions for the agent to use delimiters, such as XML tags or unique markers, to isolate untrusted user data from the rest of the prompt or tool parameters.
- Capability inventory: The skill utilizes tools for executing AI models (
model_run), managing files (upload_asset,asset_download), and performing multi-track video composition (model_scenario-compose-video). - Sanitization: No input validation, escaping, or content sanitization mechanisms are specified for the data handled by the audio models.
Audit Metadata