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 belt CLI 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-sh GitHub 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 belt command-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
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:19 PM
Security Audit — agent-trust-hub — elevenlabs-dubbing