kimi-agent-swarm-cli

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

• Third-party content exposure detected (high risk: 0.75). The required wide-search workflow can invoke WebSearch/FetchURL (and/or the local runtime/wide-search harness) to fetch public web pages whose readable text is then summarized/synthesized by the agent, creating an indirect prompt-injection path from outsider-authored free text.