openai-whisper-api

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/transcribe.sh executes curl to interact with the OpenAI API. This is the primary intended function of the skill and uses standard parameters for multipart/form-data uploads.
  • [DATA_EXFILTRATION]: The skill reads a user-specified audio file and the OPENAI_API_KEY from the environment, sending them to https://api.openai.com/v1/audio/transcriptions. Since this is the official endpoint for a well-known service, this behavior is documented as neutral and safe for the skill's purpose.
  • [SAFE]: No evidence of prompt injection, obfuscation, unauthorized persistence, or privilege escalation was found in the provided files. The script uses defensive bash settings (set -euo pipefail) and follows standard practices for a command-line tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 12:13 AM