ra-audio-to-subtitles

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes ffmpeg and ffprobe using the subprocess.run method to extract audio streams and calculate media duration. These operations use list-based arguments without a shell, which effectively prevents command injection attacks.\n- [EXTERNAL_DOWNLOADS]: The script transmits audio data to the Volcengine ASR API at openspeech.bytedance.com for transcription. This is the primary function of the skill and targets a well-known service provider.\n- [CREDENTIALS_UNSAFE]: The skill accesses sensitive API keys by parsing local .env files in the workspace. This is a standard and recommended practice for secret management in development environments, avoiding hardcoded credentials in the source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 08:47 AM
Security Audit — agent-trust-hub — ra-audio-to-subtitles