OpenAI on Tuesday revealed the rogue artificial intelligence (AI) agent that escaped its sealed evaluation environment and broke into Hugging Face’s production environment, and also hacked multiple third-party accounts and services as part of the attack. The latest disclosure shows that the security incident, which stemmed from an internal security test, was more extensive in…
Beta release versions of two npm packages in the @joyfill namespace have been compromised to deliver a remote access trojan (RAT) associated with the DEV#POPPER malware family. The list of affected packages is as follows – @joyfill/layouts@0.1.2-2773.beta.0 @joyfill/components@4.0.0-rc24-2773-beta.4 The two packages “contain an import-time JavaScript implant that resolves encrypted code
What is the Attack? A critical unauthenticated remote code execution (RCE) vulnerability affecting PTC Windchill PDMlink and PTC FlexPLM is being actively exploited by Cl0p ransomware affiliates. The attackers are targeting vulnerable Internet-facing Product Lifecycle Management (PLM) systems to deploy web shells, steal intellectual property, and carry out double-extortion ransomware attacks. The campaign chains a…
Security researcher Aleksandr Krasnov reveals dormant non-human identities can create security blind spots and releases NHI Hound, an open source tool to sniff out trust paths.
Lots of Internet-exposed server management controllers are subject to offline password-cracking attacks — and adversaries have taken note.
OpenAI’s recent AI agent sandbox escape proves traditional security principles matter more than ever: limit access, isolate execution, log everything.
Researchers propose focusing on identification of certain cognitive elements in LLMs that indicate when AI systems may take an unwanted action.
Anthropic says Claude Mythos Preview helped derive an end-to-end key-recovery attack against HAWK-256 and a 200- to 800-fold speedup for an attack on seven-round AES-128. The HAWK attack exploits a previously unused symmetry in the lattice behind the signature scheme. Anthropic’s released implementation gives an expected end-to-end runtime of about three hours and 42 minutes…
Microsoft patched a high-severity vulnerability earlier this month that allows a threat actor to escalate privileges and compromise an AD environment.
A new Mirai-derived botnet called Tengu can use a compromised Linux device’s hardware watchdog to trigger a reboot when defenders kill its main process. If that happens, Tengu’s other persistence mechanisms get another chance to relaunch it. Nozomi Networks Labs observed the dropper reaching its honeypots through Telnet credential brute force. Tengu supports 25 distributed…