accessibility_testing

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This skill performs URL-based audits using Playwright MCP (e.g., mcp__playwright__browser_navigate, mcp__playwright__browser_snapshot and related steps) against a provided target URL, meaning the agent will load and read arbitrary public web pages (third‑party/untrusted content) as part of its workflow and could therefore be exposed to indirect prompt injection from that content.