research

AI uncovers flaws in discontinued devices with no vendor left to patch them

AI uncovers flaws in discontinued devices with no vendor left to patch them 2026-11-16 at 07:00 By Anamarija Pogorelec Forescout researchers built a tool to test if generally available AI models could find security flaws on a limited budget. They examined both open-source code and compiled software whose source code was unavailable, testing an approach […]

AI uncovers flaws in discontinued devices with no vendor left to patch them Read More »

Suspected North Korean IT workers reached onboarding at companies with open data

Suspected North Korean IT workers reached onboarding at companies with open data 2026-11-13 at 09:51 By Mirko Zorz Material Security followed suspected North Korean fake IT workers through the hiring pipelines of organizations it monitors and counted 27 personas that reached onboarding over one year. At one company where a persona got that far in […]

Suspected North Korean IT workers reached onboarding at companies with open data Read More »

Attackers breached 10 organizations with an open-source AI pentest framework

Attackers breached 10 organizations with an open-source AI pentest framework 2026-11-12 at 17:00 By Mirko Zorz Chinese-speaking attackers used Cairn, an open-source AI penetration testing framework, to run 25 operations against at least 19 organizations in August and September 2026. Palo Alto Networks’ Unit 42 found that the attackers gained unauthorized access or pulled data […]

Attackers breached 10 organizations with an open-source AI pentest framework Read More »

Stolen Claude API keys can turn Claude Code into a remote-controlled implant

Stolen Claude API keys can turn Claude Code into a remote-controlled implant 2026-11-12 at 13:00 By Mirko Zorz Darktrace researchers turned Claude Code into a remote-controlled implant in a lab test, steering the coding agent through the memory stores feature of Anthropic’s Claude platform and pulling a 1 GB file out through the Claude Files […]

Stolen Claude API keys can turn Claude Code into a remote-controlled implant Read More »

AI reverse engineering let researchers add a new feature to Slack

AI reverse engineering let researchers add a new feature to Slack 2026-11-10 at 16:45 By Mirko Zorz Intezer researchers used AI agents to rebuild source code for Slack, Apple’s Finder and a TinyTurla-NG sample, from a backdoor family Cisco Talos attributes to the Turla group. They worked from the shipped programs and vendor documentation. The […]

AI reverse engineering let researchers add a new feature to Slack Read More »

AI Agents Got Root on Linux via 948 Kernel Flaws in OpenAI Research

AI Agents Got Root on Linux via 948 Kernel Flaws in OpenAI Research 2026-11-05 at 19:32 By Eduard Kovacs An unreleased OpenAI cyber model found and exploited 948 distinct Linux kernel privilege escalation bugs for about $1.2 million. The post AI Agents Got Root on Linux via 948 Kernel Flaws in OpenAI Research appeared first […]

AI Agents Got Root on Linux via 948 Kernel Flaws in OpenAI Research Read More »

A banking malware sample led researchers to an Android bug that can loop-crash phones

A banking malware sample led researchers to an Android bug that can loop-crash phones 2026-11-05 at 11:00 By Mirko Zorz Bitdefender Labs researchers built an Android app that contains no executable code and requests no permissions, and installing it leaves a Pixel 10 in a crash loop that can take a factory reset to clear. […]

A banking malware sample led researchers to an Android bug that can loop-crash phones Read More »

AI coding agents are installing MCP servers that will never be patched

AI coding agents are installing MCP servers that will never be patched 2026-11-03 at 07:45 By Mirko Zorz When a developer tells an AI coding agent to “set up a GitHub MCP,” the agent has to pick a package. New research from Glow Labs documents sessions where it picked one out of an archived repository […]

AI coding agents are installing MCP servers that will never be patched Read More »

Researchers broke the browsers built into VS Code, Cursor, Copilot, Codex and Claude Desktop

Researchers broke the browsers built into VS Code, Cursor, Copilot, Codex and Claude Desktop 2026-10-29 at 16:10 By Mirko Zorz Forever Security found ways out of the built-in browsers in five AI coding assistants: Cursor, GitHub Copilot, OpenAI’s Codex, Microsoft’s VS Code and Anthropic’s Claude Desktop. In all five, a web page or a local […]

Researchers broke the browsers built into VS Code, Cursor, Copilot, Codex and Claude Desktop Read More »

Private repos still leak secrets to Gheist, a stolen GitHub token campaign

Private repos still leak secrets to Gheist, a stolen GitHub token campaign 2026-10-27 at 12:58 By Mirko Zorz Wiz Research has recovered more than 13,500 planted branches from 850+ compromised GitHub accounts, the work of a campaign it calls Gheist, after the user agent the tool sends with its GitHub API requests. The tool takes […]

Private repos still leak secrets to Gheist, a stolen GitHub token campaign Read More »

Say a few words, and a rigged AI asks for $5,000

Say a few words, and a rigged AI asks for $5,000 2026-10-22 at 08:00 By Mirko Zorz Researchers at Imperial College London tampered with speech-to-text models so they transcribed most speakers accurately and misbehaved for one chosen person. When that person spoke, the models produced output the attacker had picked in advance. In one test, […]

Say a few words, and a rigged AI asks for $5,000 Read More »

Privacy-preserving AI can protect your heart data, the bill is the problem

Privacy-preserving AI can protect your heart data, the bill is the problem 2026-10-21 at 10:02 By Mirko Zorz A heart monitor used to be a box beside a hospital bed. Electrodes fed a cable, the cable fed a screen, and a nurse watched the screen. The threat model fit on a sticky note. Cardiac care […]

Privacy-preserving AI can protect your heart data, the bill is the problem Read More »

npm Trusted Publishing flaw exposed 1,500+ npm packages to takeover

npm Trusted Publishing flaw exposed 1,500+ npm packages to takeover 2026-10-13 at 12:00 By Mirko Zorz Bloom Security researchers found that npm’s Trusted Publishing feature let an attacker push new versions of someone else’s package without stealing a credential. The attacker only needed to register a GitHub repository name the maintainer had left behind. Bloom […]

npm Trusted Publishing flaw exposed 1,500+ npm packages to takeover Read More »

Most high-severity cloud security findings are downgraded once an AI agent checks the environment

Most high-severity cloud security findings are downgraded once an AI agent checks the environment 2026-10-13 at 07:30 By Sinisa Markovic Cloud security platforms turn every failed rule into a finding, and those findings pile up in queues sorted by severity. Research from Sola Security tested what happens to that order when each finding gets checked […]

Most high-severity cloud security findings are downgraded once an AI agent checks the environment Read More »

AI vulnerability patching has a grading problem

AI vulnerability patching has a grading problem 2026-10-12 at 07:45 By Anamarija Pogorelec Researchers at Northwestern University tested AI coding agents on 112 real security bugs. They found that a patch which stops a crash often fails the checks the project’s maintainers wrote for the fix. With Claude Opus 4.7, third of the patches that […]

AI vulnerability patching has a grading problem Read More »

Thousands of wind and solar park systems sit exposed on the internet across Europe

Thousands of wind and solar park systems sit exposed on the internet across Europe 2026-10-09 at 08:30 By Mirko Zorz Modat and NCSC-NL, the Dutch government’s cybersecurity center, found 8,547 internet-facing systems at wind farms and solar parks in 35 countries in and around the EU that should not be reachable from the internet. The […]

Thousands of wind and solar park systems sit exposed on the internet across Europe Read More »

Who watches the AI watching your street?

Who watches the AI watching your street? 2026-10-08 at 08:30 By Mirko Zorz Yusaku Fujii, a professor at Gunma University in Japan, has designed audits and penalties to stop operators from misusing AI that analyzes street camera footage. His system adds an independent record-keeper and unannounced spot checks to the AI’s outputs. Fujii’s test setting […]

Who watches the AI watching your street? Read More »

Some car apps are slipping owners’ data to big tech companies

Some car apps are slipping owners’ data to big tech companies 2026-10-01 at 12:52 By Sinisa Markovic The app that comes with your car may be sharing what it knows about you with some of the biggest tech companies. Northeastern University researchers tested 21 vehicles and 30 carmaker apps and found some sending vehicle identification […]

Some car apps are slipping owners’ data to big tech companies Read More »

Other users can watch your browsing and time your keystrokes through OS file notifications

Other users can watch your browsing and time your keystrokes through OS file notifications 2026-09-28 at 15:14 By Anamarija Pogorelec Researchers at Graz University of Technology have used the file-notification systems in Windows, Linux, and macOS to spy on activity in other accounts. On Windows, a standard unprivileged account detected 95.7 percent of another user’s […]

Other users can watch your browsing and time your keystrokes through OS file notifications Read More »

Scroll to Top