feishu-claude-code-bridge

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

• Third-party content exposure detected (high risk: 0.95). The required runtime workflow forwards Feishu/Lark chat messages (including arbitrary free-form text from other participants) into the Claude Code CLI/LLM context via the bot’s “Any other /xxx forwarded to Claude verbatim” and general message-to-claude streaming path.