New Carbonato malware uses AI agents to hijack exposed Docker hosts
A new botnet malware called Carbonato is targeting insecure hosts running Docker daemons to install the Hermes Agent AI framework and take control.
Category / AI Risk
AI Risk briefings
AI risk briefings on model misuse, deployment failures, safety regressions, governance gaps, and synthetic-media harms.
On Anthropic’s AI Misuse Report
Earlier this month, Anthropic published a long report detailing all of the Claude misuses it detected. Daniel Meissler usefully summarized the report into 117 findings. A few of the highlights: AI agents increasingly handled reconnaissan…
New RemControl Android banking malware targets users in Europe and Canada
A new Android malware-as-a-service (MaaS) platform called RemControl is targeting users through malvertising campaigns that impersonate the TVTap IPTV application.
New ClosedQuorum Windows malware uses AI for attack decisions
A new Windows malware named ClosedQuorum uses Google Gemini, DeepSeek, Qwen, and Mistral AI models to autonomously determine the actions to take during post-compromise stages of an attack.
Research on Models Engaging in Genie-Like Behavior
New paper: “Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training.” Abstract: We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language mo…
New RatHat Android malware uses AI to automate device control
A new Android malware called RatHat has been discovered, targeting users with an AI-powered subsystem that helps operators remotely navigate compromised devices.
Cisco warns of max severity ISE zero-day exploited in attacks
Cisco has released security updates to address a maximum-severity Identity Services Engine vulnerability that attackers are actively exploiting in the wild.
How Candidates Could Use AI for Good
This essay was written with Nathan E. Sanders, and originally appeared in The Guardian. There are plenty of signs that AI will make all of our experiences of the US midterm elections worse. Voters have anxiety about AI’s impacts on the c…
25 Years of Mass Surveillance Is Enough
This essay was written with Cindy Cohn, and originally appeared in Lawfare. One of the many legacies of the terrorist attacks of Sept. 11 is the government-wide shift from targeted surveillance—such as individual wiretaps or pen register…
Using AI for Weapons Development
Last week, Anthropic released a long and detailed document describing current misuses of their Claude models. I’m still reading it, but I wanted to flag this: We identified a cell of threat actors based in northern Yemen running three we…
My Talk at DEF CON
Last month, I gave a talk at DEF CON on AI hacking: what happens when AIs become hackers. It’s a combination of the potentialities I raised in my 2022 book A Hacker’s Mind and the lessons we’re learning from current AI models engaging in…
AIs Compress Exploit Timeline
Give an AI agent a mere rumor of an exploit, and it’s enough for them to find it. What’s worse, I found I could use my own agents to find the exploit just by knowing roughly what it was about and so could have been exploiting it well bef…
AIs as Modern Genies
This essay was written with Barath Raghavan, and originally appeared in Lawfare. In April, an artificial intelligence (AI) agent conducting a routine task at a company hit a snag, tried to solve it, and soon ended up deleting the company…
Microsoft Plugs Nearly 1,000 Security Holes
New security development detected from Krebs on Security. Microsoft Corp.
Hackers build AI frameworks for widescale credential theft
Threat actors are increasingly switching from AI-powered coding assistants to multi-agent frameworks that automate every stage of an attack.
Stealing AI Reasoning Traces
Interesting research: “Stealing Reasoning Traces from Proprietary LLM APIs“: Abstract: Leading large language model providers now conceal their models’ step-by-step reasoning, or chain-of-thought, to protect intellectual property and lim…
Attackers conceal phishing lures using invisible Unicode characters
Threat actors have adopted the ASCII smuggling technique in phishing campaigns, using invisible Unicode characters to evade email security filters.
Using a VM to Contain an AI Agent
It won’t work: My suspicion was that GPT 5.6-Cyber would succeed, but the frequency and manner of its success removed all doubt. We have to reassess sandboxing quality for capable AI agents, and in general the software stack with which t…
AI Coding Agents Are Installing Unknown/Untrusted Code on Corporate Networks
We cannot forget that AI coding agents are not yet trustworthy: Researchers at a stealth startup in Israel scanned 6,214 live domains belonging to defense contractors, Fortune 500, and Big Tech companies. Of the 8,265 llms.txt and llms-f…
Security Vulnerability in a Voting System
It’s a vulnerability that allows someone to recover the order of ballots cast, newly exploited with AI tools. Nearly four years since the original vulnerability was disclosed, I was still able to use it to analyze voter behavior in Georg…
AI Agents Are Now Emailing Me with Their Security Concerns
I received the two emails below earlier in the month. They’re vaguely coherent. I suppose I shouldn’t be surprised that the corpus that AIs are training on contain data suggesting that I am someone to write to with random computer and ne…
Rewiring Democracy Series on The Renovator
Nathan E. Sanders and I are writing a series of essays on real-world examples of democratic technologies for The Renovator. I haven’t been posting the full text on the blog because they’re a bit long, but here are links. Part 1 is about…
AI Doesn’t Mean the End of Mathematics—at Least Not Yet
This essay was written with Kasra Rafi, and originally appeared in The Guardian. Earlier this month, about 40 top mathematicians gathered at OpenAI’s offices to discuss the future of their profession. The meeting was off-the-record, but…
Black Hat State of Security Vendors
Andy Ellis has a roundup of the security vendors at Black Hat this year. Key Takeaways: We have entered into an AI world. While nearly half of booths didn’t directly mention AI or agents in their taglines, the effects of AI are everywher…
AI Is Learning to Write Genetic Code
This sort of research is both exciting and terrifying: The two models in question were told to generate complete genomes for a viable bacteriophage—a type of virus able to infect and replicate itself inside bacteria, destroying them from…
Detailed Timeline of OpenAI’s Cyberattack on Hugging Face
OpenAI presented details of its AI’s model’s cyberattack on Hugging Face at Black Hat last week. Simon Willison details the timeline. It’s really interesting to read through—and really impressive cyberoffense work.
How MSPs can catch phishing attacks email filters miss
AI is making phishing attacks more personalized, convincing, and difficult for traditional email filters to detect. Kaseya explains how MSPs can monitor identity, email, and endpoint activity to detect and contain attacks that make it pa…
More Incidents of AIs Going Rogue in Cybersecurity Challenges
The AI Security Institute has a new report of AI systems engaging in “unsanctioned behavior”—what I have been calling “genie behavior—while being tested on their cybersecurity capabilities. The incident stemmed from a single evaluation w…
LLMs and Contextual Integrity
I have been thinking a lot about AI and integrity. Part of that is contextual integrity. I recently found two papers on the topic. “CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs“: Abstract: L…
If the Markets Reject OpenAI and Anthropic, the US Should Nationalize Them
This essay was written with Nathan E. Sanders, and originally appeared in The Guardian. OpenAI, and then Anthropic, were each formed by AI developers who feared unrestrained corporate AI development—specifically, that companies like Goog…
Separating AI’s Technological Problems from Its Capitalism Problems
This essay was written with Nathan E. Sanders, and originally appeared in Tech Policy Press. AI represents the first time we humans can do cognitive work outside of our bodies at scale. The only comparable moment is the early years of th…
AI Genie in the Wild
When I give talks about AI genies, I use this sort of example as a hypothetical. It’s happened. The story is from Australia. Someone named Andrew tasked OpenClaw to book gym classes for him. And…. Minutes later, his AI agent reported it…
Microsoft Plugs Nearly 400 Security Holes
New security development detected from Krebs on Security. Microsoft today released updates to remedy at least 398 security vulnerabilities in its Windows operating systems and supported software, including one weakness that is already be…
Prompt Injections for Defense
This seems to work: Researchers from Tracebit on Monday said they found that placing prompt injections alongside passwords, cryptographic keys, and other secrets stored on Amazon Web Services was often all that was needed to shut down at…
AI for Military Support
Interesting empirical research: “Black Box Warfare: Human Judgment and Military Decision-Making in the Age of AI.” Abstract: How is AI transforming decision-making in modern conflict? This study provides a unique empirical window into th…
COLDCARD security audit phishing attack installs remote access tool
A phishing campaign is exploiting fears surrounding the recently disclosed COLDCARD wallet vulnerability and suspected $88.6 million Bitcoin theft to trick users into installing ScreenConnect remote access software.
ENISA scales up its role in the CVE Program
ENISA is the EU agency dedicated to enhancing cybersecurity in Europe. They offer guidance, tools, and resources to safeguard citizens and businesses from cyber threats. NATO Communications and Information Agency (NCIA), along with AI an…
How AI-powered phishing killed blocklists for good
AI is helping attackers create disposable phishing infrastructure and rapidly evolving toolkits that blocklists cannot track fast enough. Push Security explains why browser-level, technique-based detection offers a more durable defense t…
Vulnerabilities in Car Anti-Theft Device
This is disturbing: …a team of security researchers at UC San Diego, who found that a model of aftermarket car alarm known as the KARR Security System, installed in more than 2 million vehicles across the US by their estimate, can let an…
More on the OpenAI Agent’s Attack on Hugging Face
Hugging Face has published a detailed timeline of the attack. From the summary: The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchmark, which tasks an AI agent with finding and exploiting s…
Some Claude Chats Are Searchable on Google
And it’s personal information (alternate link): The exposed data includes an AI-powered therapy app that someone appears to have vibe-coded, notes on meetings, and a dashboard someone made apparently to analyze medical billing data. Expo…
The OpenAI Hack Shows the Genie Is Out of the Bottle
This essay originally appeared in Foreign Policy. Earlier this month, two of OpenAI’s models broke out of their containment sandbox and attacked another AI company. The story is kind of wild. OpenAI was running security tests on two of i…
Anthropic’s Opus 5 Is Better at Resisting Prompt Injection
The chart is interesting. On the IPI benchmark, Opus 5 improved over Opus 4.8, reducing the probability of an attacker succeeding within 15 attempts from 5.5% to 2.0%, and from 0.5% to 0.2% on 1 attempt. It also improved on Sonnet 5 (5.9…
Anthropic's Claude breached 3 orgs, uploaded PyPI malware during tests
One of Anthropic's Claude models built and uploaded a malicious Python package to PyPI during a botched security evaluation, where it ran on 15 real systems and stole credentials from a security vendor. It was one of three incidents affe…
Read This Before You Buy That TV Streaming Stick
New security development detected from Krebs on Security. Security experts have been sounding the alarm for years about the risks of using generic TV boxes that promise unlimited content streaming for a one-time fee, warning that they se…
Measuring the Tendency of AI Agents to Go Rogue
This essay was written with Barath Raghavan, and originally appeared in The Guardian. In July, Hugging Face, a company that hosts much of the world’s AI software and open-source AI models, was hacked. A malicious dataset had been used to…
OpenAI agent used exposed credentials at 4 services in Hugging Face breach
In a new update, OpenAI says its AI models also used publicly exposed credentials to compromise accounts on four third-party services during the recent attack on Hugging Face, expanding the scope of the four-day security incident to othe…
Measuring LLMs’ Ability to Perform Cryptanalysis
There’s new benchmark measuring AI’s ability to perform mathematical cryptanalysis. Anthropic’s frontier model actually found new attacks. The benchmark: “CryptanalysisBench: Can LLMs do Cryptanalysis?” The idea is to benchmark the abili…
OpenAI models used Artifactory zero-days to escape to the internet
JFrog has confirmed that OpenAI models exploited zero-day vulnerabilities in self-hosted Artifactory servers to help escape an isolated testing environment and gain access to the internet before attacking Hugging Face.
Fake Claude app promoted by Bing ads pushes SectopRAT
A malvertising campaign on the Bing search service is pushing a fake Claude desktop app installer hosted on a legitimate Claude.ai domain to deliver the SectopRAT malware.
New Dolphin X malware uses AI to rank high-value targets
A new Dolphin X remote access trojan claims to use an AI-powered profiling feature to score and rank infected users, helping cybercriminals identify which victims should be targeted first.
How enterprise GenAI can amplify ransomware risk — and how to contain it
Enterprise AI can accelerate ransomware attacks when AI assistants and agents inherit excessive permissions or compromised identities. Acronis explains how identity controls, governance, and least-privilege access help reduce AI-enabled…
CISA orders urgent action on actively exploited Langflow RCE flaw
The Cybersecurity and Infrastructure Security Agency (CISA) on Tuesday ordered U.S. government agencies to prioritize patching an actively exploited vulnerability in the Langflow visual framework for building AI agents.
MIT to Become Hotbed of AI Video Surveillance
It’s a lot: According to information obtained by The Tech, MIT is spending over $3 million on more than 500 AI surveillance cameras in academic buildings, residence halls, and outdoor areas along Memorial Drive. Installation of the new c…
On Flock License Plate Tracking Cameras
A recent story of a writer who was mistakenly identified, tracked, and arrested using data from Flock cameras has gone viral. The New Jersey plates that were allegedly stolen from the LA dealer were 34 03 DTM, not 34 10 DTM. But when the…
Protecting Privacy in an AI Era
Daniel Solove argues in the Wall Street Journal (alternate link) that giving people control of their personal data is not an effective way to regulate privacy in this era. Instead, we need to hold companies accountable for their actions,…
CISA warns admins to patch actively exploited SharePoint flaws
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) warned Tuesday that attackers are actively exploiting three vulnerabilities to hack Internet-exposed on-premises SharePoint Server instances.
Microsoft Patches a Record 570 Security Flaws
New security development detected from Krebs on Security. Microsoft Corp.
We built a vulnerability vending machine: AI tokens in, zero-days out
Intruder built an AI-powered "vulnerability vending machine" that combines code slicing with LLMs to automatically discover complex software vulnerabilities. The company explains how the system found and exploited a previously unknown Wo…
You Don't Have to Run an Exploit to Know If You're Vulnerable
Many vulnerabilities cannot be safely validated with live exploits, either because no exploit exists or the affected systems are too critical to test. Picus explains how TTP chaining helps organizations determine exploitability by valida…
Where do SMEs stand in preparing for the Cyber Resilience Act?
ENISA is the EU agency dedicated to enhancing cybersecurity in Europe. They offer guidance, tools, and resources to safeguard citizens and businesses from cyber threats. The EU Agency for Cybersecurity (ENISA) publishes the Micro, Small…
'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets
A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit,' slipped past AI code reviewers CodeRabbit and Bugbot, which never open image files at all, then convinced a co…
AI Surveillance and Social Progress
In the near future, AI-powered surveillance systems will be able to track everything we do in public, and much of what we do in private. And if we do something wrong—shoplift, litter, jaywalk, you name it—the system will notice, retain i…
New Forg365 phishing platform uses AI to target Microsoft 365 accounts
A new phishing-as-a-service (PhaaS) operation called Forg365 focuses on stealing Microsoft 365 accounts by combining adversary-in-the-middle (AiTM) and device code methods with AI-assisted lure generation.
The Language of AI Could Change How Humans Speak
Because of the way they are trained, large language models capture only a slice of human language. They’re trained on the written word, from textbooks to social media posts, and our speech as captured in movies and on television. These m…
Cybersecurity and the Gap Between Skill and Ability
Last week, national security agencies from the Five Eyes—that’s the rich, English-language-speaking countries club—jointly released a statement warning of the increasing cyber risks of AI models: in particular, their ability to autonomou…
Felons, Fraudsters Flog Offensive Cybersecurity Startup
New security development detected from Krebs on Security. A cybersecurity startup dangling millions of dollars to acquire zero-day security vulnerabilities in popular software is run by a pair of far-right conspiracy theorists and convic…
Google Is Suing Chinese Scammers Who Are Using Gemini
Not sure this will have any effect, but I support the effort: According to Google’s legal filing, Outsider Enterprise operates through Telegram. The group offers phishing-as-a-service to individuals who may not be technically savvy enoug…
JadePuffer ransomware used AI agent to automate entire attack
Researchers identified what they believe is the first documented case of a ransomware operation, JadePuffer, conducted entirely by a large language model (LLM) agent.
Flock Cameras Can Surveil Cars Without License Plates
This is from a 2024 company presentation: Officers can also tap into data showing a car’s decals, bumper stickers, back and top racks—along with temporary and unique state tags. Flock calls it a “Vehicle Fingerprint” and it’s touted as a…
New BioShocking attack manipulates AI browser into data theft
A new prompt injection attack dubbed "BioShocking" could trick AI-powered browsers into treating real-world risky actions as part of a fictional scenario, causing them to ignore any safety guardrails. A new prompt injection attack dubbed…
The Realities of AI Video Surveillance
The Financial Times has a good article on how AI is changing the capabilities of video surveillance, with information from both Israel/Iran and Russia. I wrote about this sort of thing a few years ago, how AI enables mass spying in the w…
Clean GitHub repo tricks AI coding agents into running
An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious payload that remains invisible to security scanners, AI agents, and human reviewers.
New macOS malware embeds fake errors to confuse AI analysis tools
A newly discovered macOS malware dubbed "Gaslight" is designed to confuse AI-assisted malware analysis tools by hiding prompt injection strings and fake debugging data within the executable.
Bluekit phishing kit adopts browser-in-the-middle for login theft
The Bluekit phishing-as-a-service platform continues to evolve with nearly 70 new hostnames identified over the past week and by adding browser-in-the-middle capabilities for improved data theft. The Bluekit phishing-as-a-service platfor…
Interesting Paper Exploring Prompt Injection
This is a fascinating explotation of how LLMs fall for prompt injection attacks. It turns out that they learn to recognize the style of text in different role/instruction blocks, and not just the tags. Their conclusion: Role tags were a…
Healthtech firm Xolis suffers data breach impacting 1.4 million people
Healthcare technology company Xsolis says that sensitive data belonging to nearly 1.4 million individuals was compromised in a phishing attack that gave attackers access to its network.
Stealthy Mistic backdoor linked to ransomware access broker KongTuke
A new backdoor dubbed Mistic has been observed in financially motivated attacks targeting organizations in the insurance, education, IT, and professional services sectors.
Anthropic’s Fable 5 Model Jailbroken Within Days
Fable 5 is the supposed safe version of Anthropic’s Mythos Preview, with guardrails to ensure that it can’t be used to create cyberattacks. Well, that restriction was bypassed within days.
Professional Athletes and Wearables
I haven’t thought about the privacy issues surrounding professional athletes and wearables. Wearables present serious privacy issues for “Average Joe” consumers, who are entrusting tech companies to safely store and protect their biometr…
New Prinz Eugen ransomware prioritizes recent files for encryption
A new ransomware operation named 'Prinz Eugen' prioritizes recently modified files for encryption and leaves no ransom note on the system. A new ransomware operation named ‘Prinz Eugen’ prioritizes recently modified files for encryption…
Microsoft links Mastra AI supply chain attack to North Korean hackers
Microsoft has attributed a recent Mastra AI supply chain attack that compromised more than 140 npm packages to the North Korean hacking group Sapphire Sleet, also known as BlueNoroff.
Anthropic’s Fable and the State of AI
On June 9th, Anthropic released its Fable generative AI model. Three days later, the US government classified it as a dangerous munition, and used its export-control authority to prohibit any foreign nationals from accessing it. Unable t…
‘Popa’ Botnet Linked to Publicly-Traded Israeli Firm
New security development detected from Krebs on Security. For the past four years, a sprawling Android-based botnet called Popa has forced millions of consumer TV boxes to relay Internet traffic linked to advertising fraud, account takeo…
Embedding Forbidden Text in Spyware to Discourage AI Analysis
At least one malware developer is adding text about nuclear and biological weapons to their spyware, in an effort to stop automatic AI analysis. Details: The _index.js payload begins with a large JavaScript block comment containing fake…
AI Use by the US Government
On 14 April, the Trump administration quietly acknowledged the widespread use of AI to automate government processes. The office of management and budget (OMB) disclosed a staggering 3,611 active or planned use cases for AI across the fe…
Malicious JetBrains Marketplace plugins steal AI API keys from developers
At least 15 malicious plugins found on the JetBrains Marketplace were designed to steal AI API keys from developers.
New Rokarolla Android malware targets 217 banking, crypto apps
A new Android banking trojan named Rokarolla is targeting 217 banking and cryptocurrency applications using an extensive set of 137 commands.
DOJ seizes CFAKE, SOCFAKE deepfake nude sites under TAKE IT DOWN Act
The U.S. Department of Justice announced Friday that it has seized the CFAKE.com and SOCFAKE.com websites, which allegedly hosted nonconsensual AI-generated nude images and videos of women, in what appears to be the first publicly announ…
FBI disrupts massive AI-powered phishing service using a million URLs
In a coordinated effort, the FBI, working with Google and Black Lotus Labs, has dismantled a massive Chinese phishing-as-a-service operation called Outsider Enterprise with thousands of phishing websites used to steal credit card data an…
Bernie Sanders’ AI Sovereign Wealth Fund Plan
Let no one accuse Bernie Sanders of ducking the big questions. Writing in the New York Times last week, the senator asked: “Will the future of humanity be determined by a handful of billionaires who have promoted and developed AI, with v…
A Record-Breaking Patch Tuesday for June 2026
New security development detected from Krebs on Security. Microsoft today released software updates to plug nearly 200 security holes across its Windows operating systems and supported software, a record number of fixes for the company’s…
OpenClaw AI agent found falling for phishing attacks, spills user data
Phishing simulation on an OpenClaw email agent with various configuration profiles showed that it was susceptible to tactics commonly used to compromise human users.
Anthropic’s Project Glasswing Update
In April, Anthropic initated Project Glasswing. The idea was to let companies use their new model to find and fix vulnerabilities in their own software. It was a fantastic PR move, and so many press outlets have uncritically parroted Ant…
Hacking Meta’s AI Chatbot
Hackers are convincing Meta’s AI support chatbot to let them take over other peoples’ accounts: A video posted on X showed the step-by-step process to hack someone’s Instagram account. The hacker allegedly used a VPN to spoof the targets…
AI-built ransomware toolkit automates EDR evasion, AD discovery
A threat actor is using an AI-built ransomware attack toolkit that automates Active Directory discovery and helps evade endpoint detection and response (EDR) solutions.
AI Used to Decrypt Medieval Ciphers
Researchers are using machine learning algorithms to decrypt historical pencil-and-paper ciphers.
Hackers hijack thousands of sites for ClickFix and FakeUpdate attacks
A threat actor tracked as DriveSurge has been operating large-scale malware distribution campaigns using ClickFix and FakeUpdates techniques on compromised sites.
The Intersection of Encryption and AI
As part of their 20th Anniversary celebration, Dark Reading asked five cybersecurity industry leaders who wrote blogs or columns for them over the years to select their favorite piece and share their reflections on the topic today. This…
Hackers Used Meta’s AI Support Bot to Seize Instagram Accounts
New security development detected from Krebs on Security. The Instagram accounts for the Obama White House and the Chief Master Sergeant of the U.S.
Vulnerability Disclosure in the Age of AI
New article: “Responsible Disclosure in the Age of AI: A Call for Urgent Action,” by Melissa Hathaway. Abstract: Artificial intelligence is fundamentally reshaping the balance between vulnerability discovery and remediation. Frontier AI…
GPU mining malware spreads via SEO poisoning, AI chatbots
Threat actors are targeting systems with high-performance computers in an ongoing cryptojacking campaign spread through a coordinated SEO poisoning operation that also manipulated AI chatbot recommendations.
Ghost CMS SQL injection flaw exploited in large-scale ClickFix campaign
A large-scale campaign is exploiting a critical SQL injection vulnerability (CVE-2026-26980) in Ghost CMS to inject malicious JavaScript code that triggers ClickFix attack flows. The campaign was discovered by XLab threat intelligence re…
macOS Kernel Memory Corruption Exploit
A group used Anthropic’s Mythos AI model to help find a kernel memory corruption vulnerability and exploit on Apple’s M5. News article.
US and Canada arrest and charge suspected Kimwolf botnet admin
U.S. and Canadian authorities arrested and charged a Canadian man with operating the KimWolf distributed denial-of-service (DDoS) botnet, which infected nearly two million devices worldwide.
Max-severity flaw in ChromaDB for AI apps allows server hijacking
A max-severity vulnerability in the latest Python FastAPI version of the ChromaDB project allows unauthenticated attackers to run arbitrary code on exposed servers.
Hackers earn $1,298,250 for 47 zero-days at Pwn2Own Berlin 2026
The Pwn2Own Berlin 2026 hacking contest has concluded, with security researchers collecting $1,298,250 in rewards after exploiting 47 zero-day flaws.
Bypassing On-Camera Age-Verification Checks
Some AI-based video age-verification checks can be fooled with a fake mustache.
TeamPCP hackers advertise Mistral AI code repos for sale
The TeamPCP hacker group is threatening to leak source code from the Mistral AI project unless a buyer is found for the data.
How Dangerous Is Anthropic’s Mythos AI?
Last month, Anthropic made a remarkable announcement about its new model, Claude Mythos Preview: it was so good at finding security vulnerabilities in software that the company would not release it to the general public. Instead, it woul…
KongTuke hackers now use Microsoft Teams for corporate breaches
Initial access broker KongTuke has moved to Microsoft Teams for social engineering attacks, taking as little as five minutes to gain persistent access to corporate networks.
73 Seconds to Breach, 24 Hours to Patch: The Case for Autonomous Validation
Attackers can compromise systems in minutes while patching and response still take hours or days. Picus Security breaks down why autonomous validation is becoming critical for modern defense strategies. Anthropic released its newest fron…
OpenAI’s GPT-5.5 is as Good as Mythos at Finding Security Vulnerabilities
The UK’s AI Security Institute evaluated GPT-5.5’s ability to find security vulnerabilities, and found that it is comparable to Claude Mythos. Note that the OpenAI model is generally available. Here is the Institute’s evaluation of Mytho…
Patch Tuesday, May 2026 Edition
New security development detected from Krebs on Security. Artificial intelligence platforms may be just as susceptible to social engineering as human beings, but they are proving remarkably good at finding security vulnerabilities in hum…
Shai Hulud attack ships signed malicious TanStack, Mistral npm packages
Hundreds of packages across npm and PyPI have been compromised in a new Shai-Hulud supply-chain campaign delivering credential-stealing malware targeting developers.
Google: Hackers used AI to develop zero-day exploit for web admin tool
Researchers at Google Threat Intelligence Group (GTIG) say that a zero-day exploit targeting a popular open-source web administration tool was likely generated using AI.
Hackers abuse Google ads, Claude.ai chats to push Mac
Attackers are abusing Google Ads and legitimate Claude.ai shared chats in an active malvertising campaign. Users searching for "Claude mac download" may come across sponsored search results that list claude.ai as the target website, but…
New TCLBanker malware self-spreads over WhatsApp and Outlook
A new trojan named TCLBanker, which targets 59 banking, fintech, and cryptocurrency platforms, uses a trojanized MSI installer for Logitech AI Prompt Builder to infect systems.
Why More Analysts Won’t Solve Your SOC’s Alert Problem
Attackers move faster than overwhelmed SOC teams can realistically investigate alerts. Prophet Security breaks down how AI can help analysts investigate alerts faster and focus on real threats. Your security spend has roughly doubled in…
New CVE Numbering Authorities Under ENISA Root
ENISA is the EU agency dedicated to enhancing cybersecurity in Europe. They offer guidance, tools, and resources to safeguard citizens and businesses from cyber threats. Today, four organisations have newly joined the Common Vulnerabilit…
Backdoored PyTorch Lightning package drops credential stealer
A malicious version of the PyTorch Lightning package published on the Python Package Index (PyPI) delivers a credential-stealing payload targeting browsers, environment files, and cloud services.
Telegram Mini Apps abused for crypto scams, Android malware delivery
Cybersecurity researchers have uncovered a large-scale fraud operation that uses Telegram's Mini App feature to run crypto scams, impersonate well-known brands, and distribute Android malware. Cybersecurity researchers have uncovered a l…
New Bluekit phishing service includes an AI assistant, 40 templates
A new phishing kit named Bluekit offers more than 40 templates targeting popular services and includes basic AI features for generating campaign drafts.
Official SAP npm packages compromised to steal credentials
Multiple official SAP npm packages were compromised in what is believed to be a TeamPCP supply-chain attack to steal credentials and authentication tokens from developers' systems.
Claude Mythos Has Found 271 Zero-Days in Firefox
That’s a lot. No, it’s an extraordinary number: Since February, the Firefox team has been working around the clock using frontier AI models to find and fix latent security vulnerabilities in the browser. We wrote previously about our col…
Learning from the Vercel breach: Shadow AI & OAuth sprawl
A single third-party OAuth integration can become a direct path into your environment. Push explains how the Vercel breach shows a compromised OAuth app can lead to widespread impact across downstream customers. Most organizations are ri…
What Anthropic’s Mythos Means for the Future of
Two weeks ago, Anthropic announced that its new model, Claude Mythos Preview, can autonomously find and weaponize software vulnerabilities, turning them into working exploits without expert guidance. These were vulnerabilities in key sof…
Marking 10 years of the GDPR: the evolution of the European data protection landscape
New governance development detected from EDPB News. Brussels, 27 April – Today marks the 10th anniversary of the GDPR’s adoption, the first comprehensive data protection framework spanning an entire continent, establishing clear rights f…
New npm supply-chain attack self-spreads to steal auth tokens
A new supply chain attack targeting the Node Package Manager (npm) ecosystem is stealing developer credentials and attempting to spread through packages published from compromised accounts.
Actively exploited Apache ActiveMQ flaw impacts 6,400 servers
Nonprofit security organization Shadowserver found that over 6,400 Apache ActiveMQ servers exposed online are vulnerable to ongoing attacks exploiting a high-severity code injection vulnerability.
CISA flags Apache ActiveMQ flaw as actively exploited in attacks
CISA warned that attackers are now exploiting a high-severity Apache ActiveMQ vulnerability, which was patched earlier this month after going undetected for 13 years. The U.S.
Hackers exploit Marimo flaw to deploy NKAbuse malware from Hugging Face
Hackers are exploiting a critical vulnerability in Marimo reactive Python notebook to deploy a new variant of NKAbuse malware hosted on Hugging Face Spaces.
ZionSiphon malware designed to sabotage water treatment systems
A new malware called ZionSiphon, specifically designed for operational technology, is targeting water treatment and desalination environments to sabotage their operations.
Critical Nginx UI auth bypass flaw now actively exploited in the wild
A critical vulnerability in Nginx UI with Model Context Protocol (MCP) support is now being exploited in the wild for full server takeover without authentication.
EDPB brings clarity to data processing for scientific research, speeds up the finalisation of the anonymisation guidelines and approves first European data protection seal as a tool for transfers
New governance development detected from EDPB News. Brussels, 16 April – During its latest plenary, the EDPB has adopted Guidelines on processing of personal data for scientific research purposes.
Human Trust of AI Agents
Interesting research: “Humans expect rationality and cooperation from LLM opponents in strategic games.” Abstract: As Large Language Models (LLMs) integrate into our social and economic interactions, we need to deepen our understanding o…
New AgingFly malware used in attacks on Ukraine govt, hospitals
A new malware family named 'AgingFly' has been identified in attacks against local governments and hospitals that steal authentication data from Chromium-based browsers and WhatsApp messenger. A new malware family named ‘AgingFly’ has be…
How Hackers Are Thinking About AI
Interesting paper: “What hackers talk about when they talk about AI: Early-stage diffusion of a cybercrime innovation.” Abstract: The rapid expansion of artificial intelligence (AI) is raising concerns about its potential to transform cy…
On Anthropic’s Mythos Preview and Project Glasswing
The cybersecurity industry is obsessing over Anthropic’s new model, Claude Mythos Preview, and its effects on cybersecurity. Anthropic said that it is not releasing it to the general public because of its cyberattack capabilities, and ha…
AI Chatbots and Trust
All the leading AI chatbots are sycophantic, and that’s a problem: Participants rated sycophantic AI responses as more trustworthy than balanced ones. They also said they were more likely to come back to the flattering AI for future advi…
Critical Marimo pre-auth RCE flaw now under active exploitation
A critical pre-authentication remote code execution (RCE) vulnerability in Marimo is now under active exploitation, leveraged for credential theft. Hackers started exploiting a critical vulnerability in the Marimo open-source reactive Py…
Over 20,000 crypto fraud victims identified in international crackdown
An international law enforcement action led by the U.K.'s National Crime Agency (NCA) has identified over 20,000 victims of cryptocurrency fraud across Canada, the United Kingdom, and the United States.
13-year-old bug in ActiveMQ lets hackers remotely execute commands
Security researchers discovered a remote code execution (RCE) vulnerability in Apache ActiveMQ Classic that has gone undetected for 13 years and could be exploited to execute arbitrary commands.
Cybersecurity in the Age of Instant Software
AI is rapidly changing how software is written, deployed, and used. Trends point to a future where AIs can write custom software quickly and easily: “instant software.” Taken to an extreme, it might become easier for a user to have an AI…
Is a $30,000 GPU Good at Password Cracking?
A $30,000 AI GPU doesn't outperform consumer GPUs at password cracking. Specops explains why attackers don't need exotic hardware to break weak passwords. Compute power is growing at an extraordinary pace.
Occupational health and safety: Where protection meets performance and wellbeing
Every year, millions of employees suffer illnesses and injuries that could have been prevented. As workplaces modernize, one thing remains constant: the need to protect our most valuable asset – people. Work shouldn’t come with a health…
Evolution of Ransomware: Multi-Extortion Ransomware Attacks
Multi-extortion ransomware relies on stolen data to pressure victims with public leaks. Penta Security explains how its D.AMO platform keeps exfiltrated files encrypted and useless to attackers. the University of Mississippi Medical Cent…
Claude Code leak used to push infostealer malware on GitHub
Threat actors are exploiting the recent Claude Code source code leak by using fake GitHub repositories to deliver Vidar information-stealing malware.
New CrystalRAT malware adds RAT, stealer and prankware features
A new malware-as-a-service called CrystalRAT is being promoted on Telegram, offering remote access, data theft, keylogging, and clipboard hijacking capabilities.
Claude Code source leak shows how packaging mistakes can expose AI tooling internals
Anthropic confirmed that internal Claude Code source files were exposed through an npm packaging error, turning a release workflow mistake into a supply-chain and competitive-intelligence event.
As the US Midterms Approach, AI Is Going to Emerge as a Key Issue Concerning Voters
In December, the Trump administration signed an executive order that neutered states’ ability to regulate AI by ordering his administration to both sue and withhold funds from states that try to do so. This action pointedly supported ind…
EDPB conference on cross-regulatory cooperation: what we learned
New governance development detected from EDPB News. Brussels, 23 March - On 17 March 2026, the EDPB conference “Cross-regulatory interplay and cooperation in the EU: a data protection perspective” took place in Brussels.
Team Mirai and Democracy
Japan’s election last month and the rise of the country’s newest and most innovative political party, Team Mirai, illustrates the viability of a different way to do politics. In this model, technology is used to make democratic processes…
New ISO standards bring clarity to chain of custody
Building confidence in sustainability claims worldwide. Sustainability claims are everywhere.
Digital Omnibus opinion shows EU privacy regulators will tolerate simplification but not weaker definitions
EU privacy regulators say the Digital Omnibus proposal can simplify compliance, but warn that narrowing the definition of personal data would weaken data protection.
EDPB backs global privacy statement on AI-generated imagery and harm to identifiable people
The EDPB has signed a joint Global Privacy Assembly statement warning that AI-generated imagery and video can create serious privacy, dignity, and safety harms when real people are depicted without consent.
EDPB links cross-border data-transfer rules with AI skills and governance capacity
An EDPB update on cross-border data requests and AI training signals a more operational European privacy-governance agenda for organisations handling sensitive data.
EDPB LLM privacy report signals a more operational phase of AI governance
A 2025 EDPB-backed report on LLM privacy risks focuses on concrete mitigations and real-world deployment scenarios rather than abstract AI principles.
Last 48 hours watchlist: three signals worth tracking
A security and privacy watchlist covering student cyber safety policy, AI workplace tooling risk, and emerging privacy-governance signals worth monitoring.
Privacy guardrails are becoming an AI competitiveness question
Weak privacy controls can make AI systems harder to deploy, govern, and defend over time, turning privacy into an operational AI risk question.
Why the next wave of AI security stories will be about interfaces
AI security risk is increasingly concentrated in extensions, browser flows, workplace tooling, and other user-facing interfaces rather than models alone.