qa-agent-claude

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow’s Step 1 “Explore” crawls a user-supplied application via a real browser (Playwright) and records routes/forms/text from the live site, which can include outsider-authored free text that the agent then uses in subsequent LLM steps (indirect prompt-injection risk).