elevenlabs-dialogue

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the 'infsh' (inference-sh) CLI to send dialogue segments to a remote API. These commands are well-structured and align with the stated purpose of the skill.
  • [EXTERNAL_DOWNLOADS]: The documentation references installation instructions hosted on the vendor's official GitHub repository (inference-sh/skills). This is a standard and safe practice for vendor-provided tools.
  • [PROMPT_INJECTION]: No evidence of malicious prompt injection or instructions intended to bypass safety guardrails was found. All instructions are focused on guiding the user through audio generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 09:16 PM