Search: Security vulnerability exploitation

Wide-ranging 7-zip vulnerability with 8.8 CVE rating allows for code execution — hundreds of millions of machines potentially at risk

There seems to be no end in sight for serious, wide-ranging security vulnerabilities these days. The ever-popular open-source archive-handling utility 7-Zip is now in the spotlight due…

May 28, 2026 · Bruno Ferreira

OpenAI's GPT-5.6 Sol and unreleased AI models break out of testing environment in 'unprecedented cybersecurity incident' — rogue agents hacked HuggingFace's production servers with 'thousands of individual actions across a swarm of short-lived sandboxes'

…Many professionals have even decried the industry-standard 90-day security vulnerability disclosure window as obsolete. The usual modus operandi, however, involves granting a bot access to source code repositories so it…

Jul 22, 2026 · Bruno Ferreira

Microsoft BitLocker-protected drives can now be opened with just some files on a USB stick — YellowKey zero-day exploit demonstrates an apparent backdoor

…Last month, Security researcher Chaotic Eclipse (aka Nightmare-Eclipse ) published two zero-day exploits, BlueHammer and RedSun , that made Windows Defender offer up system administrator privileges. They did this after their disclosure…

May 13, 2026 · Bruno Ferreira

2021 Honda Civic infotainment system can be jailbroken via USB — flaw uses public Android test keys to install unauthorized apps, enables for 'EvilValet' attacks

…Vulnerabilities like these have been known for years in the car industry — we have a report from eight years ago where Volkswagen refused to patch a flaw that could be exploited over…

Jun 15, 2026 · Jowi Morales

AMD silently removes memory encryption from consumer Ryzen CPUs, leaving users unaware that they may be vulnerable — security feature vanishes after newer AGESA firmware, AMD engineers go radio silent when pressed about the change

…potentially vulnerable to physical attacks. Following a months-long investigation tracked on GitHub, Ben Kilpatrick confirmed that the Transparent Secure Memory Encryption (TSME) feature — which protects CPUs against physical exploits that siphon…

Jun 17, 2026 · Etiido Uko

AI researchers trick chatbots into sharing how to make cocaine as long as they believe a user is wearing a green shirt — 'CoT Forgery' exploit spurs LLMs to divulge forbidden info by faking trusted chains of thought

…security architecture and the cognitive scaffolding of modern LLMs,” the authors note in their write-up, and the increasing load on that structure to manage LLM behavior has apparently created vulnerabilities of…

Jul 1, 2026 · Luke James

U.S. gov't orders Anthropic to disable its newest AI models worldwide due to security threats — ban on Claude Fable 5 and Mythos 5 bars access by any foreign national, even its own employees

…Independent researchers found that cheaper open-source models could replicate much of Mythos's vulnerability-finding capabilities, and a closer look at Anthropic's headline figures revealed far fewer serious exploits than…

Jun 13, 2026 · Luke James

OpenAI, Google, and Anthropic absent from Nvidia-led Open Secure AI Alliance — 30+ companies join security alliance after OpenAI agent breach

…According to the announcement, “The Open Secure AI Alliance — building on the leadership of the Linux Foundation’s Akrites initiative and OpenSSF community work — will work to remediate and disclose vulnerabilities using…

Jul 27, 2026 · Etiido Uko

Hidden backdoor in Tenda routers goes unpatched as company ignores warnings from cybersecurity researchers — Chinese company's firmware allows admin access without a password

…While CERT/CC did not disclose the hidden password itself, the existence of an undocumented secondary authentication path significantly weakens the security model of affected devices. Unlike conventional authentication vulnerabilities that stem…

Jul 8, 2026 · Etiido Uko

OpenAI took ten days to tell Hugging Face its models were behind the July 11 weekend hack, report claims — rogue AI agents reportedly active on the open Internet for several days

…The models are now known to have been running OpenAI's ExploitGym benchmark, a suite of roughly 900 tests that measures whether an AI can turn a known software bug into a…

Jul 24, 2026 · Luke James

Followed topics