webapp-testing

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

• Third-party content exposure detected (high risk: 0.80). The skill's runtime scripts (notably scripts/playwright_runner.py which calls page.goto(url) with arbitrary URLs and examples/console_logging.py which captures page console output) fetch and ingest content from open/public websites (user-provided URLs), which the tool reads and uses to determine health/status and outputs—meaning untrusted page content could influence the agent's decisions or outputs.