browser-cdp

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly navigates to and ingests arbitrary public webpages (see examples/page_scraping.py which defaults to https://news.ycombinator.com and the SKILL.md workflow that uses PageSnapshot.accessibility_tree, dom_snapshot, and BrowserActions.evaluate), and the agent reads and acts on that untrusted, user-generated content to decide clicks/typing/navigation, enabling indirect prompt injection.