elevenlabs-dubbing

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs users to download and install the required CLI tool from the vendor's official GitHub repository at raw.githubusercontent.com/inference-sh/skills/.
  • [COMMAND_EXECUTION]: Operates through the 'infsh' command-line interface to perform login and execute dubbing applications (elevenlabs/dubbing) with user-provided parameters.
  • [PROMPT_INJECTION]: Subject to indirect prompt injection risk through processing external media URLs. Evidence Chain: 1. Ingestion points: JSON input fields for audio/video URLs in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Execution of 'infsh' tool via Bash. 4. Sanitization: Not specified within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 04:25 PM
Security Audit — agent-trust-hub — elevenlabs-dubbing