feishu-chat-history

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches Feishu group messages via the Feishu IM API (see SKILL.md and references/api.md's GET /im/v1/messages), and then reads/parses and summarizes those user-generated chat messages—untrusted third-party content that can contain instructions influencing the agent's outputs.