ln-713-pip-upgrader

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and diagram.html show the worker calling external documentation/search tools (mcp__context7__query-docs, mcp__Ref__ref_search_documentation with mcp__Ref__ref_read_url, and a WebSearch fallback) to fetch migration guides and "migration steps" which the agent is expected to read and act on, exposing it to untrusted public web/community content that can influence its actions.