elevenlabs-dubbing
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates integration with the ElevenLabs dubbing API via the
beltCLI tool. All operations described are consistent with the skill's stated purpose of audio and video localization. - [EXTERNAL_DOWNLOADS]: The skill references installation instructions hosted on the
inference-shGitHub repository. These references are used for initial environment setup and target a well-known service associated with the skill's functionality. - [COMMAND_EXECUTION]: Provides examples of using the
beltcommand-line interface to process media files. These commands are standard for the platform and do not involve unauthorized privilege escalation or persistence mechanisms. - [INDIRECT_PROMPT_INJECTION]: The skill processes external media content (audio/video URLs). While this presents a theoretical surface for indirect prompt injection if the resulting transcripts are fed back into an LLM without sanitization, it is a standard characteristic of media processing tools and no active exploitation patterns are present.
Audit Metadata