browserstack

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to fetch session records, download session videos and logs, and generate screenshots of arbitrary URLs (see steps 5, 7, 12 and "Get Console / Network / Appium Logs"), which ingest untrusted/user-provided web content and logs from BrowserStack that could materially influence actions.