feishu-memory-recall

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

• Third-party content exposure detected (high risk: 0.80). This skill directly fetches and ingests user-generated messages from Feishu (see SKILL.md "search/recall/digest" and index.js functions getToken/fetchMessages which call the Feishu API and parse group/DM messages), so untrusted third‑party content is read and used to produce search results and digests that could materially influence outputs or subsequent actions.