elevenlabs-stt

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions from a GitHub repository and uses npx to add related skills from the inference-sh and belt-sh organizations. These downloads are associated with the primary service provider for this tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes audio data and text from external URLs, which constitutes an ingestion point for untrusted content.
  • Ingestion points: audio and text input fields for transcription and forced alignment (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Restricted to belt command execution via Bash.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — elevenlabs-stt