adapt-materal-enums

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly runs aptx-ft with a --base-url to fetch enum-patch.json "来自接口的枚举补丁" and then requires the LLM to read the patch comments to fill suggested_name before applying changes, so arbitrary third‑party API content can be ingested and influence downstream actions.