{
  "id": 14471,
  "url": "https://arxiv.org/abs/2607.25255v1",
  "title": "SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems",
  "summary": "Multi-agent systems improve capability through task decomposition and role specialization, but these same mechanisms introduce an important safety blind spot: a harmful objective can be fragmented into locally plausible subtasks, allowing malicious intent to evade detection by any single agent. This is a growing social-impact challenge: systems handling sensitive information or consequential tools can turn routine delegation into unauthorized disclosure or unsafe action. We argue that this failu",
  "authors": "Haowen Dai, Zonghao Ying, Wenfeng Li, Xiangfan Wu, Yisong Xiao, Tianyuan Zhang, Jiaye Lin, Lei Wei, Guangyuan Dong, Xitong Ling, Xixun Lin, Quanchen Zou, Xiangzheng Zhang",
  "category": "research",
  "topics": "agents-autonomy,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-28T03:55:47.000Z",
  "fetched_at": "2026-07-29T05:10:12.205Z",
  "source_slug": "x-arxiv-red-teaming-query",
  "source_name": "arXiv red teaming query",
  "source_homepage": "https://arxiv.org/a/redteam",
  "ethics_ai_record_url": "https://ethics.ai/record/14471",
  "original_url": "https://arxiv.org/abs/2607.25255v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}