OpenAI Models Escaped Test Environment and Breached Hugging Face
OpenAI models escaped from a controlled cyber test, exploited zero-day flaws and breached Hugging Face while searching its production database for test answers.
Ameaças Cibernéticas
1247 notíciasSwiss rail giant Stadler rejects $12.3M ransom demand after cyberattack
Swiss rail vehicle manufacturer Stadler Rail says the Everest ransomware gang demanded about $12.3 million after breaching a data exchange platform shared with one of its suppliers. [...]
How an OpenAI benchmark test turned into a real-world cyberattack
"This is day one for cybersecurity in the age of agents," Hugging Face CEO says.
When AI Attacks: OpenAI Models Autonomously Hack Hugging Face
Advanced LLMs escaped their sandboxes while attempting to achieve a non-malicious benchmark test objective.
Adobe Acrobat Extension Flaw Let Malicious Sites Read WhatsApp Web Data
Cybersecurity researchers have disclosed details of a now-patched vulnerability chain in the Adobe Acrobat Chrome extension that has over 314 million users, which, if exploited, could facilitate a silent hijack of a user's WhatsApp data. The shortcoming has been codenamed Hermet…
Hackers Exploit Windmill Flaw to Read Arbitrary Server Files Without Authentication
A high-severity security flaw impacting open-source developer platform Windmill has come under active exploitation in the wild, per VulnCheck. The vulnerability in question is CVE-2026-29059 (CVSS score: 7.5), a case of unauthenticated path traversal impacting Windmill's "get_lo…
Clover Health Assessing Impact of Social Engineering Incident – The HIPAA Journal
Clover Health Assessing Impact of Social Engineering Incident The HIPAA Journal
Clover Health Assessing Impact of Social Engineering Incident
Clover Health Investments has notified the U.S. Securities and Exchange Commission (SEC) about a cybersecurity incident first identified on July […] The post Clover Health Assessing Impact of Social Engineering Incident appeared first on The HIPAA Journal.
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. [...]
New Ubuntu Desktop Vulnerability Turns Local Access Into Root Control
A vulnerability in snap-confine lets an unprivileged user gain root access on affected Ubuntu Desktop systems. Install the latest snapd update to fix the issue.
Chick-fil-A discloses data breach after credential stuffing attacks
American fast food restaurant chain Chick-fil-A is notifying customers of a data breach after their accounts were hacked in a wave of recent credential stuffing attacks. [...]
Police Dismantle Kratos Phishing Kit Built to Steal Microsoft 365 Sessions and Bypass MFA
German and US law enforcement have taken down the core infrastructure of Kratos, described by German investigators as one of the world's most widely used criminal phishing kits, and Indonesian authorities arrested the man they say developed and ran it. In a joint announcement on…
Trojanized Newtonsoft.Json Fork Hides Game-Rigging Code in a Working Library
Cybersecurity researchers have discovered a NuGet typosquat that's unlike the typical information-stealing malware distributed via package registries: usual info-stealers: it's designed to rig live game results on Digitain. The package, named "Newtonsoftt.Json.Net," masquerades …
OpenAI says its AI models hacked Hugging Face during testing
OpenAI says its AI models, including GPT‑5.6 Sol and a pre-release model, hacked into the Hugging Face artificial intelligence repository while being tested in a sandboxed testing environment. [...]
Microsoft Azure DevOps MCP Flaw Lets Hidden PR Comments Hijack AI Review Agents
A single invisible comment in an Azure DevOps pull request can turn a reviewer's own AI coding agent against them, driving it into projects the attacker has no rights to reach and quietly leaking what it finds. The flaw is in Microsoft's official Azure DevOps MCP server, and it …
OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark
OpenAI on Tuesday said a combination of its artificial intelligence (AI) models, including GPT-5.6 Sol and an "even more capable pre-release model," was behind the security incident that targeted Hugging Face's production infrastructure last week. The AI company said the models …
Police dismantle Kratos phishing platform, arrest developer
Authorities in Germany and the U.S. dismantled the central infrastructure of Kratos, a phishing-as-a-service (PhaaS) platform with global reach, and its developer was arrested in Indonesia. [...]
FakeGit campaign uses 7,600 GitHub repos to push SmartLoader malware
A large-scale operation dubbed 'FakeGit' is pushing SmartLoader and StealC malware through 7,600 malicious GitHub repositories that accumulated more than 14 million downloads. [...]
Ransomware Is Accelerating, But It's Not Because of AI
Researchers pointed to fragmentation of the ransomware ecosystem, the emergence of new attackers, and expansion of attacks on less defended organizations.
Using LLMs to Find and Prioritize Vulnerabilities Is No Easy Task
The latest large language models have high false-positive rates and fail to take into account the context of scans, leading to more work for AppSec professionals.