browser-automation

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md workflow explicitly instructs the agent to open and navigate arbitrary URLs (browser_open_tab/browser_navigate) and to extract visible page text via browser_query (mode=page_text), which means it fetches and interprets untrusted public web content that can influence subsequent actions.