Feishu Integration Developer

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow includes Feishu webhook/event and card-callback handlers that parse and act on data.message.content / callback payloads (outsider-authored user/chat content delivered to the app), which can include arbitrary free text that may be passed into downstream LLM context if the agent uses it.