Skills
skills/inference-sh-8/skills/elevenlabs-tts/Gen Agent Trust Hub

elevenlabs-tts

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines workflows that utilize the infsh CLI tool for executing cloud-based applications, including authentication and parameter passing via shell commands.
  • [EXTERNAL_DOWNLOADS]: The documentation points to a CLI installation script hosted on the vendor's official GitHub repository (inference-sh/skills). This is a legitimate dependency for the skill's intended functionality.
  • [PROMPT_INJECTION]: The skill is designed to process arbitrary user text for speech synthesis, which introduces a surface for indirect prompt injection.
  • Ingestion points: Untrusted user input is interpolated into the --input JSON string for the infsh command in SKILL.md.
  • Boundary markers: No specific delimiters or protective instructions are provided to the agent to distinguish between user text and commands.
  • Capability inventory: The skill uses the Bash tool to interact with external APIs via the infsh utility.
  • Sanitization: The skill does not implement any validation or sanitization of the input text before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 01:59 PM
Security Audit — agent-trust-hub — elevenlabs-tts