elevenlabs-dubbing
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
beltCLI tool via Bash. Theallowed-toolsfrontmatter limits the execution context to only this specific command, which is a secure configuration.\n- [EXTERNAL_DOWNLOADS]: The skill provides links to official documentation and installation assets frominference.shand its associated GitHub repositories. These are standard resources for the service provided.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided media URLs. Ingestion points: JSON input fields in Bash commands. Boundary markers: JSON object structures. Capability inventory: Media processing via thebelttool. Sanitization: Not explicitly implemented in the skill instructions. The risk is considered low as the input is treated as a resource for dubbing rather than instructions.
Audit Metadata