form-validation-scan

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text is fetched from the runtime URL provided in the trigger (e.g., https://example.com/signup) via mcp__playwright__browser_navigate, and the subsequent mcp__playwright__browser_evaluate reads DOM text/attributes (labels, aria-describedby content, validationMessage) into the LLM context.