Attackers compromised 42 GitHub repositories by using files too large to be searched
A security research firm reported Monday that it had identified breaches of 42 third-party GitHub repositories […]
Attackers built a ‘Skynet’ AI agent that hijacks exposed models to run cyberattacks
Skynet is no longer a fictional adversary. Attackers have built an offensive agent that exploits unprotected […]
Zero Trust for Federal Agencies: Securing Mission-Critical Systems
Key Takeaways Federal Zero Trust programs must align with applicable OMB requirements, CISA guidance, and agency-specific […]
Kaspersky Finds Post-Quantum Cryptography in Lazarus Malware
Kaspersky says North Korea’s Lazarus group used NIST’s ML-KEM-1024 post-quantum standard to hide malware delivery. Here […]
Node2Shell puts Microsoft and Node.js on Brotli patch duty
A vulnerability in Google’s Brotli compression library could allow attackers to execute arbitrary code in applications […]
Alibaba AI model tried to send data to Beijing server, Cohere says
An Alibaba AI model generated an unexpected command to upload data to a Beijing-region cloud storage […]
The days of assuming another company’s breach is someone else’s problem are over
The median blast radius of data breaches has increased year-on-year at the same time cybercriminals have […]
OpenAI’s August fix for theft of reasoning traces was quickly bypassed
Cybersecurity research firm Xint on Monday published details of a bug in the OpenAI API that […]
OpenAI, Anthropic disclosures spotlight growing AI containment challenge
Two leading AI developers have released fresh evidence of a problem that researchers have long anticipated: […]
Malicious downloads can trick AI coding agents into compromising themselves
Malicious instruction files planted in a computer’s Downloads folder can trick AI coding agents into executing […]