Skills
skills/inference-sh/agent-skills/elevenlabs-dubbing/Gen Agent Trust Hub

elevenlabs-dubbing

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the infsh command-line tool to perform dubbing, speech-to-text, and video captioning tasks as part of its core functionality.
  • [EXTERNAL_DOWNLOADS]: The documentation references an installation script for the infsh CLI hosted on the vendor's GitHub repository and provides commands to add related skills via a package manager (npx skills add). These resources originate from the official vendor infrastructure.
  • [PROMPT_INJECTION]: The skill defines an ingestion surface for untrusted data through audio and video URLs provided in the input parameters.
  • Ingestion points: audio and video_url parameters in JSON inputs within SKILL.md.
  • Boundary markers: Absent from the command examples.
  • Capability inventory: Subprocess execution via the infsh CLI.
  • Sanitization: Not explicitly defined within the skill markdown body; the skill relies on the underlying platform for content validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 01:40 AM