elevenlabs-dubbing
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external resources from the service provider's infrastructure.
- It provides links to installation guidelines and documentation hosted on the inference-sh GitHub repository.
- It recommends adding the 'belt-sh/cli' skill as a prerequisite for using the dubbing features.
- [COMMAND_EXECUTION]: The skill uses the 'belt' CLI tool via Bash to perform dubbing operations, manage authentication, and list available applications.
- [INDIRECT_PROMPT_INJECTION]: The skill processes remote audio and video files provided via URL, which constitutes an ingestion point for untrusted data.
- Ingestion points: Remote media files are fetched via the 'audio' parameter in the JSON input provided to the CLI commands in 'SKILL.md'.
- Boundary markers: The skill does not implement explicit delimiters or instructions to ignore potential commands embedded within the processed media.
- Capability inventory: The skill is restricted to using the 'belt' tool within a Bash environment, which executes dubbing tasks through external API calls.
- Sanitization: There is no evidence of content sanitization or validation for the remote media files within the skill's instructions.
Audit Metadata