skills/automattic/studio/match-page/Gen Agent Trust Hub

match-page

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute commands for rendering (node scripts/run.mjs), image manipulation (magick, identify), and content management (studio wp post update, liberate_refine_report). These operations involve user-defined variables for paths and URLs.
  • [COMMAND_EXECUTION]: The tool mcp__plugin_playwright_playwright__browser_evaluate is used to execute script logic within the browser to extract layout metadata.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external URLs, posing a risk of indirect prompt injection. 1. Ingestion points: sourceUrl, previewUrl, and parity-log.json. 2. Boundary markers: None present to isolate external content. 3. Capability inventory: Bash (command execution), Edit (file modification), and WordPress database updates. 4. Sanitization: No filtering of external HTML/CSS is specified.
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to external domains via Playwright tools to retrieve and render pages for visual comparison.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 03:02 AM
Security Audit — agent-trust-hub — match-page