BodySnatcher: The Most Severe AI Vulnerability Yet Let Attackers Hijack Fortune 500 AI Agents
A hardcoded credential and broken authentication in ServiceNow let attackers impersonate any user and weaponize AI agents to create admin backdoors.
Tag
#agentic-ai
OpenAI Built a Bunker for ChatGPT Because It Can't Fix the Walls
ChatGPT's new Lockdown Mode protects against prompt injection data theft - but OpenAI admits the underlying vulnerability may never be solved. Here's what that means for agentic AI.
Nebius Pays $275 Million for Tavily, Betting That AI Agents Need Their Own Search Engine
The ex-Yandex AI cloud company acquires a one-year-old Israeli startup to bring real-time web search into its platform for autonomous AI agents.
341 Malicious AI Agent Plugins Were Hiding in Plain Sight on ClawHub
OpenClaw's skills marketplace was weaponized to steal passwords and crypto wallets. A single attacker published 314 fake tools. This is what happens when AI agents get app stores.
Your AI Agent Is the New Insider Threat
AI agents can access sensitive data, execute trades, and delete backups without human oversight. Most companies aren't ready for what happens when they go wrong.