skills/sfrmrc/skills/elevenlabs-tts/Gen Agent Trust Hub

elevenlabs-tts

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill manages authentication via environment variables and .env files, which is a standard security practice for local tools. It avoids hardcoding secrets and limits network communication to the official ElevenLabs API (api.elevenlabs.io).
  • [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The helper script scripts/generate_voice.py relies exclusively on Python standard libraries and does not perform any remote code execution or download unverified packages.
  • [DYNAMIC_EXECUTION]: The skill does not use eval(), exec(), or any other dynamic code execution techniques. User-provided text is strictly treated as data for speech synthesis.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes user-controlled text, the output is restricted to audio generation through a specialized API, posing no risk of instruction leakage to executable contexts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 01:36 PM
Security Audit — agent-trust-hub — elevenlabs-tts