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 explicitly instructs automated web research and URL reading (Phase 1.4 in SKILL.md and the Automatic Analysis Guide) using WebSearch and mcp__Ref__ref_read_url and also falls back to WebFetch of raw.githubusercontent.com for missing reference files, so it will ingest public third‑party web content that can influence recommendations and downstream actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs at runtime to fetch required reference files when local shared/ is missing via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those fetched documents are marked "MANDATORY READ" and used to control runtime contracts and prompts, so this remote URL is a runtime external dependency that directly controls agent instructions.