whisper-transcribe

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the execution of the whisper-transcribe shell command to perform its primary function of transcribing media files.
  • [EXTERNAL_DOWNLOADS]: The skill downloads machine learning models from the Hugging Face Hub (huggingface.co) upon its first use. These downloads are from a well-known service and are necessary for the skill's operation.
  • [COMMAND_EXECUTION]: Installation documentation suggests running shell commands for environment setup, including pip install and chmod.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it transcribes untrusted media content into text that is subsequently processed by the agent.
  • Ingestion points: Audio and video files (SKILL.md)
  • Boundary markers: None identified for the transcription output
  • Capability inventory: System command execution via subprocess calls (SKILL.md)
  • Sanitization: No explicit sanitization of transcribed content is provided
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 08:19 PM
Security Audit — agent-trust-hub — whisper-transcribe