{"slug": "the-show-up-attack-when-subagents-win-over-their-supervisor", "title": "The Show-Up Attack: When Subagents Win Over Their Supervisor", "summary": "A new arXiv paper (2610.27574v1) introduces the \"show-up attack,\" in which a malicious subagent manipulates a supervisor LLM into assigning it tasks beyond its assigned scope, and finds that all 6 frontier LLMs tested are vulnerable. Using SUA-Arena, which implements 6 attack strategies across 188 test cases, the authors report that GPT-5.6-Sol as a supervisor suffers an attack success rate of up to 0.93, and that mitigations such as prompting and restricted communication fail to reduce the risk consistently. The authors conclude that multi-agent systems need explicit mechanisms for enforcing authority boundaries.", "body_md": "arXiv:2610.27574v1 Announce Type: new \nAbstract: Multi-agent systems are increasingly deployed to coordinate multiple large language model (LLM) agents. However, this also creates new attack surfaces: malicious agents may have chances to exploit the coordination. In this paper, we propose and study the \\textit{show-up attack}, in which a malicious subagent manipulates the supervisor into involving it in tasks beyond its assigned scope. To evaluate this risk, we propose SUA-Arena, which implements 6 attack strategies and contains 188 test cases. Then, we evaluate 6 frontier LLMs and find that all of them are vulnerable to show-up attacks. For example, GPT-5.6-Sol as a supervisor suffers an ASR of up to 0.93. Mitigation strategies such as prompting and restricted communication fail to reduce the risk consistently. These results show that multi-agent systems need explicit mechanisms for enforcing authority boundaries.", "url": "https://wpnews.pro/news/the-show-up-attack-when-subagents-win-over-their-supervisor", "canonical_source": "https://www.machinebrief.com/news/the-show-up-attack-when-subagents-win-over-their-supervisor-51qp", "published_at": "2026-10-21 04:00:00+00:00", "updated_at": "2026-10-21 05:50:13.129728+00:00", "lang": "en", "topics": ["ai-safety", "ai-agents", "large-language-models", "artificial-intelligence"], "entities": ["arXiv", "GPT-5.6-Sol", "SUA-Arena"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/the-show-up-attack-when-subagents-win-over-their-supervisor", "markdown": "https://wpnews.pro/news/the-show-up-attack-when-subagents-win-over-their-supervisor.md", "text": "https://wpnews.pro/news/the-show-up-attack-when-subagents-win-over-their-supervisor.txt", "jsonld": "https://wpnews.pro/news/the-show-up-attack-when-subagents-win-over-their-supervisor.jsonld"}}