distill-to-skill

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to "Fetch the URL and read the full content" and to explore public articles, blogs, and GitHub repos (Step 1 / description), which clearly ingests untrusted third‑party web content that can influence the agent's subsequent actions.