Google Reports First Autonomous AI Cyberattack by Russian Hackers
An AI system identified vulnerabilities, created exploits, and executed attacks without human intervention.
AI-assisted coverage comparison, editor-supervised · How this was made

Foto: Profimedia
Photograph: Digi 24 (embedded from source)
What this story says
- An AI system named exploit_agent has autonomously discovered software vulnerabilities, created exploits, and executed attacks without human input, according to Google Threat Intelligence Group.
- Russian-speaking hackers are identified as the operators behind this first-of-its-kind autonomous AI cyberattack.
- The attack targeted French websites within the media, entertainment, and education sectors.
- Google warns that this marks the arrival of autonomous AI cyberattacks, which could become increasingly common.
Who covered it
Percentages are shares of the 31 outlets carrying a published leaning rating. 76 of the 107 outlets we know ran this story carry no rating and are not counted in them. Coverage measured .
Trust
42/100
Craft
60/100
Hype
45/100
107 sources · methodology
Google's Threat Intelligence Group has reported the first instance of a cyberattack conducted entirely by artificial intelligence. The AI system, identified as exploit_agent, autonomously analysed security patches, discovered vulnerabilities, developed methods to exploit them, and executed the attacks without any human intervention. This development signifies a new frontier in cyber warfare, where AI operates independently to breach systems.
The operators behind this autonomous AI cyberattack have been attributed to Russian-speaking hackers. The targets of this attack were French websites across the media, entertainment, and education industries. Google has issued a warning that the era of autonomous AI cyberattacks has begun and is likely to become a more frequent occurrence.
Disagreement on specific targets
While Google Threat Intelligence Group reported that the attack targeted French sites in the media, entertainment, and education sectors, some digests did not specify the targets. For example, VentureBeat stated the report names no exploited flaw or victim count. Other digests, such as detector.media, specified the French media, entertainment, and education sectors.
What the coverage left out
None of the left-rated digests mention the specific sectors targeted by the attack. Similarly, none of the centre-rated digests specified the targeted sectors, with VentureBeat explicitly stating the report names no victim count. While some right-rated digests mentioned the targets, others, such as the New York Post and India Today, did not specify which sectors were attacked.
Still developing. We have re-checked which outlets are covering this 6 times, most recently on 17 Nov 2026, 23:45, and will add the sides that appear.
How other outlets pictured it
Which photograph to run is each newsroom’s own choice. The leaning beside a name is that outlet’s published rating, not a claim that the pictures divide along it. Every picture is shown from the outlet’s own server and links to the article it ran in.
How each side covered it
Our own reading of the reporting listed below, written from the outlets’ articles rather than quoted from them. The reasoning is set out on our methodology page.
Left
8 rated outlets
- Left-rated reports highlighted the autonomous nature of the AI and the minimal human involvement. IBTimes UK reported that Google confirmed an AI framework built and ran a credential-stealing attack in under six hours, grabbing thousands of logins with barely a human involved. United24 and TVN24.pl both cited Politico in reporting that Russian-speaking hackers used AI for what may be the first fully automated cyberattack without human intervention. TNW noted Google's statement that attackers used AI alone to turn patches into exploits, and that it is 'highly likely' attackers will continue using such frameworks. Detector.media focused on Google recording the first fully automated AI cyberattack by Russian-language attackers against French media, entertainment, and education sites.
Centre
12 rated outlets
- Centre-rated reports focused on Google's warning about the arrival of autonomous AI threats and the mechanism of the attack. The Hill reported Google's statement that 'the era of autonomous attacks has arrived' and that AI models are executing multiple attack stages autonomously. Hindustan Times noted that attackers are using large language models to compare code before and after updates, shrinking the window for organisations to patch flaws. UPI highlighted Google's detection of fully AI-automated cyberattacks for the first time. Cointelegraph stated that attackers are using AI to analyse security patches and develop exploits, reducing the time for organisations to update systems. CyberScoop reported Google's assertion that Russian-speaking hackers ran the first fully automated AI cyberattack using exploit_agent. VentureBeat mentioned that Google stated attackers built exploit_agent, an AI framework that diffs patches and runs exploits unaided, but noted the report names no exploited flaw or victim count. ZN.UA Зеркало недели reported Google stating Russian-speaking hackers carried out the first fully automated cyber attack with AI.
Right
11 rated outlets
- Right-rated reports often focused on the 'first' aspect of the autonomous attack and the involvement of Russian hackers. The New York Post reported that Google caught hackers using AI to 'fully automate vulnerability discovery and exploitation without a human in the loop for the first time.' India Today stated Google found exploit_agent using LLMs to analyse patches and launch attacks autonomously, showing defenders have less time to secure unpatched software. OKDIARIO reported Google catching cybercriminals who use AI to attack without anyone by their means, with the AI finding and exploiting failures alone. Korrespondent.net mentioned Google announcing the first cyber attack in history where AI sought vulnerability and hacked into software. Yonhap News Agency reported Google's 'First Confirmation of Autonomous AI Hacking Attack Without Human Intervention.' Sapo stated that for the first time, an AI will have conducted a full-on cyberattack on its own, used by attackers who write in Russian. Realitatea.net reported Russian-speaking hackers carried out the first cyber attack where AI identified and exploited vulnerabilities without human intervention. Tippinsights noted Google researchers said attackers are moving toward autonomous, multi-agent frameworks capable of executing complex intrusions at greater speed.
Questions about this coverage
- How did the left and right cover Google Reports First Autonomous AI Cyberattack by Russian Hackers?
- Of the 31 outlets on this story carrying a published leaning rating, 26% are rated left, 38% are rated centre, 36% are rated right. Those percentages are shares of the rated outlets, not of every outlet that ran it, which was 107. The sections above set out what each side emphasised, in its own terms.
- Is Google Reports First Autonomous AI Cyberattack by Russian Hackers left or right?
- Neither side dominates it. Of the 31 rated outlets on this story, 26% are rated left, 38% are rated centre, 36% are rated right, and no side holds the 70% this site would want before calling a field one-sided. A story is not left or right in any case; the outlets that carried it are what carry ratings.
- Is the coverage of Google Reports First Autonomous AI Cyberattack by Russian Hackers biased?
- Google Reports First Autonomous AI Cyberattack by Russian Hackers is one event reported by 107 outlets, and this page does not rate the story as biased or unbiased. What it publishes is the spread: which outlets ran it, where named rating organisations place each of them on the spectrum, and what each side chose to lead with. A leaning rating describes an outlet's record over time, not this article, and the two should not be run together.
- Which outlets covered Google Reports First Autonomous AI Cyberattack by Russian Hackers?
- 107 that we know of, every one of them listed further up this page with a link to its own report and to what we hold on the publisher. Nothing here is a summary of somebody else's summary: the outlets are named so the original reporting can be read.
- What is exploit_agent?
- Exploit_agent is an AI system identified by Google Threat Intelligence Group that autonomously discovers software vulnerabilities, creates exploits, and executes cyberattacks without human intervention. It analyses security patches to identify and exploit flaws.
- Who is behind the first autonomous AI cyberattack?
- Russian-speaking hackers are attributed by Google as the operators behind the first fully automated AI cyberattack. This marks a significant development where AI systems are used independently to carry out cyber intrusions.
- What types of sites were targeted in the attack?
- The cyberattack, conducted autonomously by AI, targeted French websites within the media, entertainment, and education sectors. This indicates a potential shift in the types of targets for AI-driven cyber threats.
- What is Google's warning regarding AI cyberattacks?
- Google warns that the era of autonomous AI cyberattacks has arrived and that such attacks could become increasingly common. This development necessitates advanced automated defenses and reshapes cybersecurity strategies.
Read it at the source
107 outlets, grouped by the leaning a published rating gives them. Every headline links to the original; an underlined outlet name opens our profile of that publisher.
Left
8- Russian-Speaking Hackers Launched First Fully Automated AI Cyberattack, Google Says (opens United24 in a new tab)
- Google Has Recorded a Cyberattack that Hackers Have Fully Automated with AI for the First Time (opens detector.media in a new tab)
detector.media — is detector.media biased? Our profile of this outlet
- The First Fully Autonomous Cyberattack: Russian-Speaking Hackers Create a New AI Agent (opens TVN24.pl in a new tab)
- Google Confirms AI Ran Cyberattack With Almost No Human Intervention To Steal Thousands of Logins (opens IBTimes UK in a new tab)
IBTimes UK — is IBTimes UK biased? Our profile of this outlet
- Google says attackers used AI alone to turn patches into exploits (opens TNW in a new tab)
- The First Fully Automated Cyber Attack Carried Out with AI, Reported by Google. Suspicions Go in the Direction of Russia - HotNews.ro (opens Hot News in a new tab)
- Russian-Speaking Hackers Launched the First Fully Automated, AI-Based Cyber Attack, Google Announces (opens antena3.ro in a new tab)
antena3.ro — is antena3.ro biased? Our profile of this outlet
- Google says Russian speakers pulled off first-ever fully automated AI cyberattack (opens Politico Europe in a new tab)
Politico Europe — is Politico Europe biased? Our profile of this outlet
Centre
12- Google: ‘The era of autonomous attacks has arrived’ (opens The Hill in a new tab)
- Google Says Hackers Use AI Agents to Find and Exploit Software Flaws (opens Cointelegraph in a new tab)
Cointelegraph — is Cointelegraph biased? Our profile of this outlet
- In a first, Google detects AI-automated cyberattack (opens UPI in a new tab)
- Threat actors using AI to mount cyberattacks, often without human help: Google (opens Hindustan Times in a new tab)
Hindustan Times — is Hindustan Times biased? Our profile of this outlet
- Google says Russian-speaking hackers ran the first fully automated AI cyberattack (opens CyberScoop in a new tab)
CyberScoop — is CyberScoop biased? Our profile of this outlet
- Google: AI built to turn patches into exploits (opens VentureBeat in a new tab)
VentureBeat — is VentureBeat biased? Our profile of this outlet
- Russian-Speaking Hackers Carried Out the First Fully Automated Cyber Attack with I.I. (opens ZN.UA Зеркало недели in a new tab)
ZN.UA Зеркало недели — is ZN.UA Зеркало недели biased? Our profile of this outlet
- Google: Russian-Speaking Hackers Would Have Carried Out the First Fully Automated Cyber Attack with Artificial Intelligence (opens Digi 24 in a new tab)
Show 4 more
- Google Finds an AI Agent That Turned Security Patches Into Exploits With No Human Help (opens WebProNews in a new tab)
WebProNews — is WebProNews biased? Our profile of this outlet
- Google: AI agent turned a security patch into a working exploit with no human help (opens The Register in a new tab)
The Register — is The Register biased? Our profile of this outlet
- Agentic AI frameworks push hacking threat to ‘inflection point,’ Google warns (opens Cybersecurity Dive in a new tab)
Cybersecurity Dive — is Cybersecurity Dive biased? Our profile of this outlet
- Google warns that fully-automated AI attacks are coming soon (opens BleepingComputer in a new tab)
BleepingComputer — is BleepingComputer biased? Our profile of this outlet
Right
11- NEW: Google Issues Ominous Warning Amid String Of Cyber Outages (opens TrendingPolitics in a new tab)
TrendingPolitics — is TrendingPolitics biased? Our profile of this outlet
- Russian AI bots pull off first fully automated cyber attack — and Google caught them (opens New York Post in a new tab)
New York Post — is New York Post biased? Our profile of this outlet
- Google Warns Fully Autonomous AI-Powered Cyberattacks Could Soon Become Common (opens tippinsights in a new tab)
tippinsights — is tippinsights biased? Our profile of this outlet
- Russian-Speaking Hackers Were Suspected in a Historical Cyber Attack. (opens Korrespondent.net in a new tab)
Korrespondent.net — is Korrespondent.net biased? Our profile of this outlet
- The Age of Autonomous Attacks with AI Has Arrived: Google First Catches Hackers Who Find and Exploit Failures without Anyone Behind (opens OKDIARIO in a new tab)
- "For the First Time," an AI Will Have Conducted a Full-on Cyberattack on Its Own (opens Sapo in a new tab)
- Google says hackers are using AI agents to weaponise security patches without human intervention (opens India Today in a new tab)
India Today — is India Today biased? Our profile of this outlet
- Google "First Confirmation of Autonomous AI Hacking Attack Without Human Intervention" (opens 연합뉴스-Yonhap News Agency in a new tab)
연합뉴스-Yonhap News Agency — is 연합뉴스-Yonhap News Agency biased? Our profile of this outlet
Show 3 more
- AI Finds Vulnerabilities and Even Launches Attacks… Google: “Human-Free Autonomous Hacking Becomes a Reality” (opens Unknown in a new tab)
Unknown
- Google recorded the first fully automated cyberattack using AI (opens news-pravda.com in a new tab)
news-pravda.com — is news-pravda.com biased? Our profile of this outlet
- Google: Russian-Speaking Hackers Used AI for the First Fully Automated Cyber Attack (opens REALITATEA.NET in a new tab)
REALITATEA.NET — is REALITATEA.NET biased? Our profile of this outlet
Not rated
76- Google GTIG Attributes to Russian Speakers the First Cyberattack with Autonomous AI End to End without Human in the Loop (opens Moncloa in a new tab)
- Have Agentic Cyberattacks Crossed a Threshold for the Space Economy? (opens New Space Economy in a new tab)
New Space Economy — is New Space Economy biased? Our profile of this outlet
- Google Finds AI Framework Configured to Automate Patch-Based Exploits. (opens TokenPost in a new tab)
- Google Warns Fully Autonomous AI-Powered Cyberattacks Could Soon Become Common (opens BizToc in a new tab)
- AI Hacking Bots Now Breaking into Networks, FBI and Google Sound the Alarm (opens Lynnwood Times in a new tab)
Lynnwood Times — is Lynnwood Times biased? Our profile of this outlet
- Google Unveils First Fully AI Automated Cyberattacks (opens der Standard DE in a new tab)
der Standard DE — is der Standard DE biased? Our profile of this outlet
- Agentic AI Attacks: The Era of Autonomous Attacks (opens İndigo Dergisi in a new tab)
İndigo Dergisi — is İndigo Dergisi biased? Our profile of this outlet
- Google Discovers Exploit_agent: Attacks with AI Agents in Europe (opens Cyber Security 360 in a new tab)
Cyber Security 360 — is Cyber Security 360 biased? Our profile of this outlet
Show 68 more
- Google: AI Turns Security Fixes Into Automated Attacks (opens nyadagbladet.se in a new tab)
nyadagbladet.se — is nyadagbladet.se biased? Our profile of this outlet
- AI Attack without Humans: Google Reveals Autonomous "Exploit_agent" (opens t3nMagazin in a new tab)
t3nMagazin — is t3nMagazin biased? Our profile of this outlet
- Google Warns Hackers Could Launch AI-Powered Cyberattacks Without Human Help (opens Insider Paper in a new tab)
Insider Paper — is Insider Paper biased? Our profile of this outlet
- Google Threat Intelligence Group Reports Shift Toward Autonomous AI Cyber Operations (opens Hyperight in a new tab)
- Google Calls It a Milestone: AI Agents Carried Out Cyberattacks without Human Help (opens computerworld.dk in a new tab)
computerworld.dk — is computerworld.dk biased? Our profile of this outlet
- Google Reported the World's First Autonomous AI Attack by Russian-Speaking Hackers on European Sites (opens Mind.ua in a new tab)
- Google Warns of AI-Driven Cyberattacks (opens computersweden.se in a new tab)
computersweden.se — is computersweden.se biased? Our profile of this outlet
- Artificial Intelligence Developed a Cyberattack without Human Intervention. (opens Habertürk in a new tab)
- Google Warning. Hackers Use Artificial Intelligence for Fully Automated Cyber Attacks. What Targets Were Targeted (opens Mediafax in a new tab)
- Russian Hackers Carried Out Cyber Attack by AI for the First Time (opens Unknown in a new tab)
Unknown
- Google Says Hackers Used AI to Fully Automate a Cyberattack (opens techloy.com in a new tab)
techloy.com — is techloy.com biased? Our profile of this outlet
- Google Warns: Russian-Speaking Hackers Launched the First Fully Automated Cyber Attack with AI (opens PSnews in a new tab)
- Google says hackers use AI agents to find and exploit software flaws (opens BITRSS in a new tab)
- Automated Software Exploitation with AI: Risk Companies (opens The Cryptonomist in a new tab)
The Cryptonomist — is The Cryptonomist biased? Our profile of this outlet
- Hackers Have Taught AI to Find Vulnerabilities and Carry Out Attacks without Human Intervention (opens dev.by in a new tab)
- Hacker on Vacation: Now the Attacks Launch AI Alone, Warns Google (opens Punto Informatico in a new tab)
Punto Informatico — is Punto Informatico biased? Our profile of this outlet
- The First Fully Automated Cyberattack by AI Agents Was Detected - Techmaniacs (opens techmaniacs.gr in a new tab)
techmaniacs.gr — is techmaniacs.gr biased? Our profile of this outlet
- Google finds attackers using AI agents for autonomous exploitation (opens TechNode Global in a new tab)
TechNode Global — is TechNode Global biased? Our profile of this outlet
- IA Cyberattacks: Companies Have Less Time to Install Their Patches (opens economiematin.fr in a new tab)
economiematin.fr — is economiematin.fr biased? Our profile of this outlet
- Google Discovers Autonomous AI Agents Targeting French Sites (opens Cryptoast in a new tab)
- AI Tools Enhance Cyberattacks, Warns Google (opens The CSR Journal in a new tab)
The CSR Journal — is The CSR Journal biased? Our profile of this outlet
- Google: Russian-Speaking Hackers Launched the First Fully Automated Cyberattack Using AI (opens flash.gr in a new tab)
- Google: Russian-Speaking Hackers Launched the First Autonomous AI Cyberattack (opens LiFO in a new tab)
- Live Hacker No Longer Needed: Google Unveils New Type of AI Cyberattack (opens naTemat.pl in a new tab)
naTemat.pl — is naTemat.pl biased? Our profile of this outlet
- Google Observes Fully Automated Cyberattacks with AI Technology (opens Heise in a new tab)
- Google Issues Alarm: AI Supposedly Launched Cyberattack Alone. Trail Leads to Russian-Speaking Hackers (opens rmf24.pl in a new tab)
- Google: First AI Agent Developed without Human Intervention, Automatically Exploiting Vulnerabilities. (opens rti.org.tw in a new tab)
rti.org.tw — is rti.org.tw biased? Our profile of this outlet
- Google warns of autonomous AI attacks finding flaws (opens itbrief.in in a new tab)
itbrief.in — is itbrief.in biased? Our profile of this outlet
- Google warns of autonomous AI attacks finding flaws (opens SecurityBrief Asia in a new tab)
SecurityBrief Asia — is SecurityBrief Asia biased? Our profile of this outlet
- Google warns of autonomous AI attacks finding flaws (opens SecurityBrief New Zealand in a new tab)
SecurityBrief New Zealand — is SecurityBrief New Zealand biased? Our profile of this outlet
- Google warns of autonomous AI attacks finding flaws (opens SecurityBrief Australia in a new tab)
SecurityBrief Australia — is SecurityBrief Australia biased? Our profile of this outlet
- Google warns of autonomous AI attacks finding flaws (opens IT Brief Asia in a new tab)
IT Brief Asia — is IT Brief Asia biased? Our profile of this outlet
- Google warns of autonomous AI attacks finding flaws (opens IT Brief New Zealand in a new tab)
IT Brief New Zealand — is IT Brief New Zealand biased? Our profile of this outlet
- Google warns of autonomous AI attacks finding flaws (opens IT Brief Australia in a new tab)
IT Brief Australia — is IT Brief Australia biased? Our profile of this outlet
- Policy: For the First Time Russian-Speaking Hackers Conducted a Fully Automated Cyber Attack with I.I. (opens NEWSru.co.il in a new tab)
NEWSru.co.il — is NEWSru.co.il biased? Our profile of this outlet
- Google warns autonomous cyberattacks have arrived (opens Crypto Briefing in a new tab)
Crypto Briefing — is Crypto Briefing biased? Our profile of this outlet
- Google says attackers used AI to turn patches into exploits with no human (opens Phil's Stock World in a new tab)
Phil's Stock World — is Phil's Stock World biased? Our profile of this outlet
- Report: Cyber Criminal Use of AI Increasingly Sophisticated (opens govtech.com in a new tab)
govtech.com — is govtech.com biased? Our profile of this outlet
- Autonomous AI Cyberattacks Arrive in 6 Months, Says Google (opens SempreUPdate in a new tab)
SempreUPdate — is SempreUPdate biased? Our profile of this outlet
- Google Claims that "Russian-Speaking Hackers" Have Carried Out the First Fully Automated Cyber Attack with the Help of AI (opens n1info.rs in a new tab)
- You're Putting Off Updating. According to Google, AI Is Running Out of Patience. (opens ITHardware in a new tab)
ITHardware — is ITHardware biased? Our profile of this outletOpinion
- Google Finds Hackers Using AI Agents to Build and Run Exploits From Software Patches (opens cybernoz.com in a new tab)
cybernoz.com — is cybernoz.com biased? Our profile of this outlet
- Google Claims that Russian Speakers Succeeded in the First Fully Automated IA-Based Cyber Attack (opens TVR MOLDOVA in a new tab)
TVR MOLDOVA — is TVR MOLDOVA biased? Our profile of this outlet
- “Google”: Rusakalbiai Programmišiai Vykdė Pirmąją Visiškai Automated DI Kibernetinę Ataką - Verslo žInios (opens vz.lt in a new tab)
- Google warns that fully automated cyberattacks have arrived and will get worse fast (opens The Decoder in a new tab)
The Decoder — is The Decoder biased? Our profile of this outlet
- Google Sees AI Agent Develop Exploits Autonomously (opens Enterprise Sec Tech in a new tab)
Enterprise Sec Tech — is Enterprise Sec Tech biased? Our profile of this outlet
- Google Turns on Alarms: AI Could Launch Cyberattacks without Human Help (opens Hipertextual in a new tab)
Hipertextual — is Hipertextual biased? Our profile of this outlet
- Cyberattacks without Humans: Google Documents Fully Autonomous Attacks (opens the-decoder.de in a new tab)
the-decoder.de — is the-decoder.de biased? Our profile of this outlet
- Google Discovers the First Hacker Attack Conducted by an Artificial Intelligence without Humans: Affected French Sites, Russian Clues (opens notiziegeopolitiche.net in a new tab)
notiziegeopolitiche.net — is notiziegeopolitiche.net biased? Our profile of this outlet
- Terrorist – Politics: Russians Created AI Hackers Who Attack without the Involvement of People (opens inpolitics.ro in a new tab)
inpolitics.ro — is inpolitics.ro biased? Our profile of this outlet
- The era of autonomous attacks has arrived (opens India Shorts in a new tab)
India Shorts — is India Shorts biased? Our profile of this outletOpinion
- Google Detects the First Fully Automated Cyberattack with Artificial Intelligence (opens VilaWeb.cat in a new tab)
VilaWeb.cat — is VilaWeb.cat biased? Our profile of this outlet
- Google Warns: Russian-Speaking Hackers Launched the First Fully Automated Cyber Attack with Artificial Intelligence (opens Adevarul in a new tab)
- Google Says Russian-Speaking Hackers Carried Out First Fully Automated AI (opens LB.ua in a new tab)
- Google: Russian-Speaking Hackers Launched the First Fully Automated Cyber Attack with AI (opens spotmedia.ro in a new tab)
spotmedia.ro — is spotmedia.ro biased? Our profile of this outlet
- Google: "Russian-Speaking Hackers" Carried Out the First Fully Automated AI Cyberattack | Pandora's Box (opens koutipandoras.gr in a new tab)
koutipandoras.gr — is koutipandoras.gr biased? Our profile of this outlet
- Google: Russian-Speaking Hackers Likely Ran First Fully Automated AI Cyberattack on French Sites (opens upday in a new tab)
- Google Discovered Something Unprecedented: Hackers Developed an AI Agent that Independently Carries Out Cyberattacks (opens Večernji list in a new tab)
Večernji list — is Večernji list biased? Our profile of this outlet
- Agentic AI frameworks push hacking threat to ‘inflection point,’ Google warns | #hacking | #cybersecurity | #infosec | #comptia | #pentest | #ransomware - National Cyber Security Consulting (opens National Cyber Security in a new tab)
National Cyber Security — is National Cyber Security biased? Our profile of this outlet
- Google Threat Intelligence Group Identifies First Known Instance of Autonomous AI Framework Turning Security Patches Into Working Exploits (opens OODA Loop in a new tab)
- Google Reveals How Hackers Are Using AI Agents to Automate Real-World Cyberattacks (opens Cyber Security News in a new tab)
Cyber Security News — is Cyber Security News biased? Our profile of this outlet
- Exploit_agent: AI Generated an Exploit From Patches. (opens TechInside in a new tab)
TechInside — is TechInside biased? Our profile of this outlet
- Google: AI agent turned a security patch into a working exploit with no human help (opens databreaches.net in a new tab)
databreaches.net — is databreaches.net biased? Our profile of this outlet
- Google: AI agent turned a security patch into a working exploit with no human help (opens IT Security News in a new tab)
IT Security News — is IT Security News biased? Our profile of this outlet
- Google Warns that an AI Agent Created an Exploit From a Patch without Human Help (opens DiarioBitcoin in a new tab)
DiarioBitcoin — is DiarioBitcoin biased? Our profile of this outlet
- Google Says AI Automated the Jump From Patch to Exploit (opens The Defiant in a new tab)
The Defiant — is The Defiant biased? Our profile of this outlet
- Google says an AI framework turned security patches into exploits with no human in the loop (opens SiliconANGLE in a new tab)
SiliconANGLE — is SiliconANGLE biased? Our profile of this outlet
- Google Finds Hackers Using AI Agents to Build and Run Exploits From Software Patches (opens The Hacker News in a new tab)
The Hacker News — is The Hacker News biased? Our profile of this outlet
How did this read?
About the coverage, not about the story. We do not ask whether you agree with what happened — we have no honest use for that answer.



