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 a setup guide hosted on the official GitHub repository for the inference-sh organization.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
beltCLI commands to perform authentication and trigger media processing apps. - [INDIRECT_PROMPT_INJECTION]: The skill processes external media files provided via URL, which represents a potential entry point for untrusted data into the workflow.
- Ingestion points: The
audioparameter in the JSON input fields withinSKILL.md. - Boundary markers: No specific delimiters or safety warnings are present in the examples.
- Capability inventory: Shell command execution via the
beltCLI. - Sanitization: No explicit sanitization or validation of the input URL content is defined in the instructions.
Audit Metadata