agency-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 handling (e.g., src/webhook/event-dispatcher.ts parsing data.message.content and data.action.value from incoming Feishu events/card callbacks), which are outsider-authored free text/messages from other users/parties and are then read into the agent’s LLM context via the bot command text path (handleBotCommand(chatId, text)).