{"id":816335,"date":"2026-10-28T08:50:15","date_gmt":"2026-10-28T08:50:15","guid":{"rendered":"https:\/\/www.newsbeep.com\/uk\/816335\/"},"modified":"2026-10-28T08:50:15","modified_gmt":"2026-10-28T08:50:15","slug":"ai-hacker-finds-4-severe-bugs-in-popular-industrial-control-software-in-under-4-hours","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/uk\/816335\/","title":{"rendered":"AI ‘hacker’ finds 4 severe bugs in popular industrial control software in under 4 hours"},"content":{"rendered":"

<\/p>\n

\n security\n <\/p>\n

<\/a><\/p>\n

\n One critical, three high-severity EPICS bugs could disrupt research experiments\n <\/p>\n

An autonomous AI agent discovered four vulnerabilities in the decades-old, widely used EPICS (Experimental Physics and Industrial Control System) open source software toolkit, including a critical flaw that could allow remote attackers to execute code on systems used to control particle accelerators and fusion experiments.<\/p>\n

The bugs include a critical, 9.8-rated under CVSS v3.1 integer overflow vulnerability (CVE-2026-114595<\/a>), leading to an attacker-controlled out-of-bounds heap write and potentially remote code execution; an 8.2-rated, high-severity, improper message-length validation flaw (CVE-2026-114596<\/a>), causing an out-of-bounds memory write and controller-process crash; a 7.5-rated, high-severity insufficient bounds checking bug (CVE-2026-114597<\/a>) that allows out-of-bounds memory reads and process crashes; and a 7.5-rated, high-severity type confusion flaw (CVE-2026-114598<\/a>) that can lead to denial of service and could expose adjacent memory contents.\u00a0<\/p>\n

All four affect EPICS Base, which is used to operate some of the world’s largest scientific research projects and facilities, and organizations should update to version 7.0.11, which includes the fixes.<\/p>\n

\u201cSuccessful exploitation of these vulnerabilities could allow an attacker to cause a denial-of-service condition, corrupt memory, disclose sensitive information, or potentially execute arbitrary code,\u201d the US Cybersecurity and Infrastructure Security Agency (CISA) warned<\/a> in a Tuesday advisory.\u00a0<\/p>\n

An AI agent called Cipher independently found all four previously unknown security holes – investigating and testing the unfamiliar EPICS system, and validating the four exploits – in three hours and 49 minutes, Causal Security co-founder Shubham Raj told The Register.<\/p>\n

\u201cThe initial investigation required no human intervention, followed by one instruction authorizing deeper exploitability testing in a secure environment,\u201d Raj said.<\/p>\n

Earlier this year, Causal Security\u2019s Cipher, which Raj described as \u201ca fully autonomous super hacker that can reason across the technology stack,\u201d found multiple critical attack paths in power-grid systems used across North America and Europe, prompting an October 8 security advisory<\/a> from CISA.<\/p>\n

EPICS, originally developed by Los Alamos National Laboratory and Argonne National Laboratory, is used to build and remotely control distributed Supervisory Control and Data Acquisition (SCADA) systems, connecting operators to physical devices. It\u2019s used in around 90<\/a> major scientific, university, and industrial projects and facilities globally including A<\/a>rgonne National Laboratory’s Advanced Photon Source<\/a> and ITER’s fusion reactor control system<\/a>.\u00a0<\/p>\n

All four of these flaws illustrate how AI agents are really good<\/a> at finding vulnerabilities in industrial and operational technologies<\/a>\u00a0– systems and equipment that used to be able to rely on obscurity to protect them from hackers<\/a> – and add to defenders’<\/a>\u00a0concerns that it’s only a matter of time until an autonomous cyberattack shuts down critical services<\/a>, like power grids or water systems. These are the types of digital intrusions that can cause physical harm.<\/p>\n

Raj points to CVE-2026-114595, the critical integer-overflow vulnerability, as an example. \u201cIt allows attacker-controlled network data to cause an out-of-bounds heap memory write, with potential for remote code execution,\u201d he told us.<\/p>\n

\u201cEPICS controllers sit between operators and physical equipment, handling measurements, commands, and control functions,\u201d he continued. \u201cOperationally: Imagine a particle accelerator in the middle of an expensive experiment. An attacker could potentially crash a controller, interrupt critical measurements or control functions, and force operators to halt the experiment. That could mean lost experimental work, significant downtime, and expensive recovery.\u201d<\/p>\n

Plus, if an attacker was able to develop an RCE exploit, this could allow them to \u201ctake control of the affected process, manipulate readings, interfere with control functions, or disrupt the equipment connected to it,\u201d Raj said.<\/p>\n

The prerequisite for exploiting these vulns in a real scientific facility is being able to reach the vulnerable EPICS services on a facility’s control network. But this could occur if the networks weren\u2019t sufficiently segmented, or another system had access to the vulnerable EPICS network.\u00a0<\/p>\n

\u201cOnce an attacker is able to find a network, which is either misconfigured or they are able to reach, it\u2019s pretty easy to carry out the attacks,\u201d Raj said, adding that exploitation wouldn\u2019t require deep OT knowledge, or understanding of how particle accelerators or fusion reactors work. \u201cSomeone with conventional exploitation skills could investigate them, and increasingly capable AI systems could help develop exploits without requiring specialized OT expertise.\u201d<\/p>\n

Manipulating specific physical processes does require additional knowledge, he added. \u201cBut an attacker doesn’t need to understand the physics of a particle accelerator to disrupt the software controlling it. Crashing critical processes or interrupting monitoring and control can already have serious operational consequences. What’s changing is that attackers may no longer need years of specialized expertise just to discover these weaknesses.\u201d \u00ae<\/p>\n","protected":false},"excerpt":{"rendered":"security One critical, three high-severity EPICS bugs could disrupt research experiments An autonomous AI agent discovered four vulnerabilities…\n","protected":false},"author":2,"featured_media":816336,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[554,733,4308,86,56,54,55],"class_list":["post-816335","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-technology","tag-uk","tag-united-kingdom","tag-unitedkingdom"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/816335","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=816335"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/816335\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/816336"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=816335"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=816335"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=816335"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}