chrome-expert

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs programmatic navigation and scraping of arbitrary web pages and responses (e.g., Page.navigate / Fetch.getResponseBody in references/cdp.md, Playwright/Puppeteer page.goto in references/headless.md, and host_permissions like "https:///" in references/extensions/mv3-overview.md), so the agent would read and act on untrusted third‑party content that could carry indirect prompt injection.