team-frontend-debug

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly navigates to arbitrary target URLs (see roles/reproducer/role.md and specs/debug-tools.md using mcp__chrome-devtools__navigate_page) and collects DOM snapshots, console messages and network responses that roles/analyzer and roles/fixer must read and act on, so untrusted third‑party web content can materially influence agent decisions and tool use.