agent-discovery

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

• Third-party content exposure detected (high risk: 0.90). The skill's Verification Checklist and workflow explicitly instruct fetching and inspecting public sites (e.g., "curl -sL https://example.com/page", "curl -I https://example.com/sitemap.md", and checks of robots.txt / search indexing"), which requires the agent to read and act on arbitrary open/public third-party content that can influence its decisions.