specialist-engineering-feishu-integration-developer

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md’s runtime workflow only spawns a specialist agent with a fixed developer prompt and passes through “{the user's question},” with no indication of the agent ingesting outsider-authored free text from external feeds/queues (e.g., email/chat/tickets) before selecting a specific item.