elevenlabs-voice-isolator

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the infsh CLI tool to perform audio processing via the ElevenLabs platform. This is the intended functionality of the skill and is documented in the usage examples.\n- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection (Category 8).\n
  • Ingestion points: The audio input parameter accepts external URLs provided by users or other agent steps, as seen in SKILL.md.\n
  • Boundary markers: No specific delimiters or instructions are provided to ensure the agent ignores potential commands that might be embedded in the processed audio data (e.g., if the output is subsequently transcribed).\n
  • Capability inventory: The skill is granted permission to execute system commands via the Bash(infsh *) tool definition.\n
  • Sanitization: The skill does not implement input validation or content sanitization for the retrieved audio data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 01:19 PM
Security Audit — agent-trust-hub — elevenlabs-voice-isolator