video-podcast-producer

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses ffmpeg commands to perform video processing tasks such as trimming, concatenating segments, and resizing for Shorts. These commands are integral to the skill's primary function and are documented with specific parameters like stream copying for efficiency.- [DATA_EXFILTRATION]: Instructions include interacting with YouTube Studio via a browser extension to automate metadata entry. This process targets a well-known service and emphasizes that the user must manually select files for upload and confirm visibility settings before publishing, which maintains user oversight and prevents automated data exfiltration.- [PROMPT_INJECTION]: The workflow involves processing transcriptions of user-provided recordings. The skill includes a 'Wait for user approval' step after analyzing the transcription but before executing any cut commands, which serves as a human-in-the-loop safeguard against instructions potentially hidden in audio content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 05:08 PM
Security Audit — agent-trust-hub — video-podcast-producer