feishu-bot-builder

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

• Third-party content exposure detected (high risk: 0.80). The skill's required runtime handlers explicitly ingest and interpret untrusted user/third-party content—e.g., do_p2_im_message_receive_v1 in SKILL.md parses incoming chat messages to dispatch commands and references/cards.md shows /webhook/card handlers that process card action payloads—so external messages/webhooks can materially influence bot behavior.