form-validation-scan

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted content from external websites (form definitions and page snapshots) via Playwright MCP tools.
  • Ingestion points: mcp__playwright__browser_evaluate and mcp__playwright__browser_snapshot read HTML structure and page text from user-specified URLs.
  • Boundary markers: No specific delimiters or safety instructions are used to separate website content from agent instructions, creating a surface for indirect prompt injection.
  • Capability inventory: The skill uses Playwright tools to navigate, fill forms, and click elements on arbitrary URLs.
  • Sanitization: The skill does not perform sanitization on the external content before processing it.
  • [COMMAND_EXECUTION]: The skill executes JavaScript within the browser context using the mcp__playwright__browser_evaluate tool.
  • Evidence: The workflow includes a JavaScript snippet to inventory forms and fields: () => [...document.forms].map(f => ({ ... })). This is a standard use of browser automation tools for auditing purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 04:07 PM
Security Audit — agent-trust-hub — form-validation-scan