testing-e2e

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly navigates to and ingests arbitrary target URLs (see "Generate Test" spawn prompt with "URL: {target URL}" and the "Record Session"/"Navigate to target URL" steps) and uses the page DOM/state to generate tests and make decisions, exposing the agent to untrusted third‑party content that could carry indirect prompt injection.