skills/ingpoc/skills/transcribe/Gen Agent Trust Hub

transcribe

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill correctly handles sensitive information by instructing users to manage their OPENAI_API_KEY via local environment variables, avoiding credential exposure in the interaction history.
  • [COMMAND_EXECUTION]: The skill executes a bundled Python script (transcribe_diarize.py) to handle the transcription logic, which is a standard and transparent approach for this functionality.
  • [EXTERNAL_DOWNLOADS]: The skill uses the official openai package from the public PyPI registry, which is an expected and trusted dependency.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted audio data from external files. 1. Ingestion points: audio files loaded in scripts/transcribe_diarize.py. 2. Boundary markers: none. 3. Capability inventory: scripts/transcribe_diarize.py performs file reads and network communication with OpenAI's API. 4. Sanitization: none.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 09:45 AM
Security Audit — agent-trust-hub — transcribe