refactoring-code

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

• Third-party content exposure detected (high risk: 0.70). The skill's refactor-strategist/refactor-reviewer workflow (see ./references/refactoring-web-resources.md and the Progressive Disclosure Map in SKILL.md) explicitly fetches and reads public web pages (e.g., martinfowler.com, refactoring.com, blog posts) at runtime to justify design or split decisions, exposing the agent to untrusted third-party content that can influence its decisions.