og-image-builder

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts for route discovery and image generation.
  • [DATA_EXFILTRATION]: No external network communication was detected; data processing is confined to the local project.
  • [EXTERNAL_DOWNLOADS]: The skill uses the playwright package and Chromium browser, which are reputable tools.
  • [PROMPT_INJECTION]: The skill ingests file metadata to create images, which creates a surface for indirect injection. Ingestion points: extracted metadata in scripts/analyze_codebase.py. Boundary markers: None used in the image templates. Capability inventory: local file access and Playwright browser rendering. Sanitization: none performed on extracted strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 01:13 PM
Security Audit — agent-trust-hub — og-image-builder