[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-open-cyber-range-reveals-frontier-ais-can-breach-real-networks":10},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":22,"tags":24,"sources":28,"feedback":32,"feedback_at":22,"cost_usd":32,"total_tokens":32},1205,"open-cyber-range-reveals-frontier-ais-can-breach-real-networks","Open cyber range reveals frontier AIs can breach real networks","A new benchmark shows leading AI models can exploit web apps and move laterally across simulated enterprise hosts, highlighting emerging offensive risk.","- Frontier AI models are now being tested in a realistic cyber‑range environment.\n\nThe researchers released AgentCyberRange, an open suite that links 15 web applications with 156 internal hosts across eight enterprise‑style networks. The suite contains 110 known vulnerabilities and a toolchain called Cage for running, orchestrating and verifying attacks. Six top‑tier AI systems were given identical prompts and budget limits and asked to perform two stages: discover and exploit web services, then expand footholds inside the network. The best performer, GPT‑5.5 with Codex, succeeded on 16.1% of web exploits and 31.7% of post‑exploitation tasks; giving it more concrete hints lifted those scores to 33.0% and 46.3%.\n\nThis matters because prior benchmarks only measured isolated tricks like CTF puzzles, missing the full intrusion workflow that matters to defenders. Demonstrating that off‑the‑shelf AIs can navigate a multi‑host environment suggests a lower barrier for automated, large‑scale attacks and gives security teams a concrete yardstick for emerging threats.\n\nThe study also uncovered previously unknown bugs in popular projects, underscoring that open, reproducible ranges are becoming essential for early risk detection.","[\"ai\",\"cybersecurity\",\"benchmarks\"]","2026-06-15T04:00:00.000Z","2026-06-16T17:50:24.528Z","2026-06-16T17:50:27.352Z","published",null,[],[25,26,27],"ai","cybersecurity","benchmarks",[29],{"name":30,"url":31},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.14295",0]