og-image

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from project configuration and source files (e.g., package.json, CSS variables, branding assets) to drive the image generation and metadata update process. This represents a standard surface for code-analysis tools.
  • Ingestion points: Phase 1 (Codebase Analysis) extracts framework data, design tokens, and product descriptions from local project files.
  • Boundary markers: None explicitly defined for the processed data; the skill relies on standard agent parsing logic.
  • Capability inventory: Includes file creation (Phase 2), browser control for screenshots (Phase 3), and layout file modification (Phase 4).
  • Sanitization: The skill does not define specific sanitization or validation for project-extracted strings before interpolation into metadata or browser navigation.
  • [SAFE]: The skill utilizes browser tools to navigate to a local development route and capture screenshots, which is a benign use of agent capabilities for asset generation.
  • Evidence: Phase 3 describes the use of browser_navigate, browser_resize, and browser_take_screenshot against localhost to generate the OG image asset.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:03 PM