kernel-cli

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly runs browser automation and scraping of arbitrary web pages (e.g., "kernel browsers playwright execute <session_id> 'await page.goto("https://example.com\")'" in references/browser-management.md and the high-volume scraping loop in references/browser-pools.md) and accepts user-provided URLs/payloads for app invocations (references/app-deployment.md), so it ingests untrusted public web content that the agent is expected to read/interpret.