elevenlabs-dubbing
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
beltCLI tool within a Bash environment to perform authentication (belt login) and execute dubbing tasks (belt app run elevenlabs/dubbing). These commands are necessary for the skill's primary function of media processing. - [EXTERNAL_DOWNLOADS]: The documentation references external installation instructions hosted at
raw.githubusercontent.com/inference-sh/skills. This is used to guide the user through the setup of the required command-line interface. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of audio and video URLs provided in the JSON input.
- Ingestion points: The
audioparameter in the input JSON (SKILL.md). - Boundary markers: None identified in the provided instructions.
- Capability inventory: Execution of the
beltCLI tool via Bash (SKILL.md). - Sanitization: Relies on the underlying CLI tool and the ElevenLabs API to handle potentially malicious media content or metadata.
Audit Metadata