refactor-java-07-api-naming

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

• Third-party content exposure detected (high risk: 0.75). Runtime LLM context can include outsider-authored free text from the target codebase itself: the skill scans and reports findings from Java source files (controllers/DTOs) that are authored by parties other than the operating user, and those file contents/derived strings are fed into the agent for check/repair planning.