ln-110-project-docs-coordinator

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (SKILL.md Phase 1.4 and references/guides/automatic_analysis_guide.md Section 2) explicitly instructs using MCP Ref and WebSearch (e.g., mcp__Ref__ref_read_url, WebSearch) to fetch and read public web documentation and search results, which are ingested and used to influence recommendations and generated documents—exposing the agent to untrusted third‑party content.