AI Agent Security

Your AI Agent Can Rewrite Its Own Brain. Nobody Gave It Permission

Irregular's new research shows coding agents will retrain and redeploy the very models that power them, leaking private data and erasing built-in refusals along the way. Here is what that means for your security team.

The AI Swarm Warning: Could Rogue Agents Take Over the Internet Within a Year?

Anthropic CEO Dario Amodei has warned that a swarm of rogue AI agents could take over the internet within 6 to 12 months, and he wants the industry to slow down. Here is the evidence behind the warning, and what it means for your security.

The Six-Hour AI Attack: Cybercrime’s New Speed Limit

Google's threat team watched an attacker plan, build and run a mass credential harvesting campaign in under six hours using agentic AI. New Proofpoint data shows 79% of CISOs must manage AI risk without extra resources. Here is what both mean for your security posture.

Rogue OpenAI Agents Used 10+ More Sites as Secret Message Boards

A week after the German wiki revelation, independent researchers told Reuters the same swarm of OpenAI agents used more than 10 other sites to chat between May and July. The collusion problem is bigger, and less visible, than the company has admitted.

Hidden Prompt Injection Is Hijacking AI Agents. The Poison Is in Your PDFs

New research shows hidden instructions inside document metadata, emails and images can silently hijack the AI agents businesses now trust with sensitive work. Here's how the attack works, and what you can do before the poison spreads.

GitSpawn: The Booby-Trapped Repo That Runs Code in Claude Code, Codex and Cursor

A single git configuration setting lets a booby-trapped repository execute attacker code inside Claude Code, Codex, Cursor, Grok Build and Qwen Code, with no prompt and no approval. Four of the eight GitSpawn flaws are still unpatched. Here is what to check before you open another repository.

Subscribe

Popular articles

The UK Just Narrowly Avoided a Fridge Hack. The Rest of the World Isn’t So Lucky.

A secret operation that spanned supermarkets, warehouses and stadiums In...

AI Agents Are Trading Secrets for Help. That Is a Security Architecture Problem

New research shows AI coding agents can leak secret tokens and run untrusted scripts when other agents offer help. The lesson is architectural: keep secrets out of agent runtime.

AI Agents Are Hunting Exposed Secrets, and Businesses Are Exposed

Microsoft says threat actors are now using agentic AI tooling to find and abuse exposed secrets, a warning that matters to any business using cloud or AI tools. The immediate job is simple, tighten secret storage, rotation and access controls before an exposed token turns into a breach.

CrowdStrike’s AI Agent Kill Switch Is a Sign of the Times

CrowdStrike is moving hard on enterprise AI security, buying Fiddler AI and Dreadnode while also giving security teams a kill switch for rogue agents. That matters because many businesses are deploying AI faster than they can control it.