elevenlabs-tts

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill points to installation guidelines and related resources hosted on the inference-sh GitHub repository and the inference.sh platform.
  • [COMMAND_EXECUTION]: The skill operates using the belt CLI tool. Execution is restricted to commands starting with belt via the allowed-tools policy.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text for audio synthesis via the belt command's input parameters (ingestion point in SKILL.md). No boundary markers or sanitization steps are explicitly defined in the instructions, and the tool has shell execution capabilities restricted to the belt prefix (capability).
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 05:51 AM