
Security
Vulnerabilities, attacks and defenses.
Page 13


US Army Cyber Command is developing self-spreading AI agents

Meta Muse flaw exposes personal and business secrets in shared conversations

OpenAI spy reportedly worked for Saudi Arabia: Arrest warrant issued

US orders civilian federal agencies to remove DeepSeek from their systems

Microsoft outlines security approach to the 'agentic insider' threat

AI agents hacked over 100 websites, including John Deere and SharkNinja

AI agents broke into 100+ sites for one hacker at $50 each, researcher says

Microsoft unveils security tools to monitor and corral rogue AI agents

OpenAI: Rogue AI seized an unauthorized crypto wallet

OpenCode hacked: User credentials leaked

An OpenAI model hacked a government site and quietly downloaded 24 years of hospital data

XBOW used GPT-5.6 Sol to build a $250,000 Chrome exploit in six days

EU sends information requests to OpenAI and Anthropic after agent hacks

OpenAI in early talks to acquire security firm Trail of Bits

OpenAI agent used crypto from an account it didn't own to complete a task

Perplexity open-sources SPACE, a sandbox platform for AI agents

OpenAI models hacked a crypto wallet and breached more websites
