elevenlabs-voices

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads audio files from the well-known ElevenLabs API endpoint (api.elevenlabs.io).
  • [DATA_EXFILTRATION]: Accesses the ElevenLabs API key from the local environment, .env files, or the OpenClaw configuration (~/.openclaw/openclaw.json) to authenticate requests to the official synthesis service.
  • [COMMAND_EXECUTION]: Provides several Python utility scripts (tts.py, sfx.py, setup.py, voice-design.py) that perform local file operations and network requests when executed.
  • [PROMPT_INJECTION]: The skill processes untrusted text input for conversion to audio, representing a surface for indirect prompt injection.
  • Ingestion points: User-provided text through the --text argument in scripts/tts.py and the --prompt argument in scripts/sfx.py.
  • Boundary markers: Absent; the skill does not wrap inputs in delimiters or provide instructions to the API to ignore embedded commands.
  • Capability inventory: The skill is capable of network communication (urllib.request) and writing audio data to the local file system.
  • Sanitization: No input validation or sanitization is performed on the text before it is sent to the synthesis model.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 01:00 PM