page-weight-budget

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs technical performance audits on user-specified URLs using the Playwright MCP. It collects network request data and evaluates DOM properties such as script tags, stylesheets, and image dimensions to generate a budget report.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes content from external websites.
  • Ingestion points: Website metadata and resource lists are ingested via mcp__playwright__browser_network_requests and mcp__playwright__browser_evaluate as described in SKILL.md.
  • Boundary markers: Absent. The skill does not explicitly instruct the model to ignore potential instructions embedded in the analyzed page's metadata or headers.
  • Capability inventory: The skill utilizes Playwright to navigate, evaluate scripts in the browser, and read network traffic.
  • Sanitization: None. Resource URLs and metadata from the target site are processed directly for the report.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 04:06 PM
Security Audit — agent-trust-hub — page-weight-budget