elevenlabs-dubbing
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation guidelines and resources from the official inference-sh GitHub repository and the inference.sh domain for its core functionality.
- [COMMAND_EXECUTION]: The skill utilizes the 'belt' command-line interface to perform audio and video processing, which includes logging into the service and running specific applications.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing external media URLs.
- Ingestion points: Audio and video URLs provided in the JSON input field in
SKILL.md. - Boundary markers: Data is structured using JSON formatting.
- Capability inventory: Uses the
beltCLI via the Bash tool to interact with remote APIs. - Sanitization: No explicit sanitization or validation of the input URLs is defined within the markdown instructions.
Audit Metadata