audio-transcribe

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill transcribes untrusted audio data which enters the agent context.
  • Ingestion points: audio_file (transcribe.py).
  • Boundary markers: Absent; output is raw text.
  • Capability inventory: File system read/write, subprocess execution via uv run.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:22 PM