core-fix-skill-docs

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent (agent-browser CLI or WebFetch) to fetch and extract documentation from the public site docs.rs (e.g., "https://docs.rs/{crate_name}/...") and save that third‑party, author-generated content into skill references, so untrusted external content would be read and could influence subsequent actions.