video-perception

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a legitimate workflow for video analysis using the codex-video-vision MCP server tools.
  • [SAFE]: Instructions for using tools like video_analyze and video_watch are focused on optimizing frame extraction and audio transcription.
  • [SAFE]: No evidence of data exfiltration, prompt injection, or malicious command execution was found.
  • [SAFE]: Metadata provided in the YAML frontmatter and the agents configuration file is consistent with the skill's purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 01:05 AM
Security Audit — agent-trust-hub — video-perception