elevenlabs

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external text data from VOICEOVER-SCRIPT.md to generate audio assets, creating a surface for potential instructions embedded in the script data.
  • Ingestion points: Reads the VOICEOVER-SCRIPT.md file through the /generate-voiceover toolkit command.
  • Boundary markers: The instructions do not define specific markers to delimit user-provided text from agent instructions.
  • Capability inventory: The skill performs network operations via the ElevenLabs SDK and writes multiple files to the local disk, including MP3s and metadata JSON files.
  • Sanitization: No explicit sanitization or validation of the input script content is described.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of local scripts and system tools for audio workflow management.
  • References the execution of python tools/voiceover.py to automate scene-based audio generation.
  • Recommends using ffmpeg for audio format conversion and post-processing tasks.
  • [EXTERNAL_DOWNLOADS]: The skill initiates network communication with ElevenLabs official API endpoints to facilitate audio synthesis and voice management services.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 12:09 AM
Security Audit — agent-trust-hub — elevenlabs