openai-whisper-api

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses curl to communicate with the official OpenAI API at api.openai.com. This is the intended functionality for an OpenAI-related transcription tool and targets a well-known service domain.
  • [COMMAND_EXECUTION]: The script scripts/transcribe.sh executes curl to send audio data for processing. The script implements robust argument parsing and strictly quotes all variables to prevent shell injection or word-splitting issues.
  • [CREDENTIALS_UNSAFE]: The skill requires an OPENAI_API_KEY for authentication. It correctly instructs the user to provide this via an environment variable or a local configuration file, adhering to standard security practices for local tool execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 11:30 PM
Security Audit — agent-trust-hub — openai-whisper-api