desktop-controller

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

• Third-party content exposure detected (high risk: 0.90). The skill's Playwright engine explicitly fetches and interacts with arbitrary external URLs (see scripts/playwright_control.py web-open/web-click/web-eval/web-inspect and SKILL.md/README examples) and the agent reads DOM content and screenshots (page.evaluate, page.title, and "Claude Vision" visual verification) to decide and perform follow-up actions, so untrusted web content can materially influence the agent's actions and enable indirect prompt injection.