webapp-testing

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

• Third-party content exposure detected (high risk: 0.90). The skill includes a runtime script (scripts/playwright_runner.py) that is explicitly invoked with arbitrary URLs (e.g., python scripts/playwright_runner.py <url> --screenshot --a11y), which causes the agent to fetch and interact with untrusted public web content as part of its workflow.