ln-821-npm-upgrader

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent (see "MCP Tools for Migration Search" and Phase 4/6) to query external sources—mcp__context7__query-docs, mcp__Ref__ref_search_documentation, and WebSearch—to fetch migration guides and community/official docs from the open web (e.g., GitHub, web search) and requires using those fetched guides before applying automated code migrations, so untrusted third‑party content can directly influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly falls back at runtime to WebFetch files from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, which are fetched during execution as required "shared" dependencies and could directly control agent behavior or provide executable content.