elevenlabs-dubbing
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the inference.sh CLI installation instructions hosted on GitHub and utilizes the
beltCLI tool for its core functionality. These resources are part of the intended service platform. - [COMMAND_EXECUTION]: The skill uses the Bash tool to execute
beltCLI commands. Access is restricted to thebeltcommand space via theallowed-toolsconfiguration, which is a standard implementation for CLI-based skills. - [INDIRECT_PROMPT_INJECTION]: The skill processes external media files (audio/video URLs) provided in the input. While this represents a data ingestion surface, the processing is performed by the external ElevenLabs/inference.sh services, posing a low risk for direct prompt injection attacks against the local agent.
Audit Metadata