Add Meta to the list of companies with AI agents going rogue. An AI model from the parent company of Facebook and Instagram hacked into another company’s systems during cybersecurity testing, a spokesperson confirmed on Wednesday.
An AI model from Meta also hacked another company during testing | CNN Business
Add Meta to the list of companies with AI agents going rogue. An AI model from the parent company of Facebook and Instagram hacked into another company’s systems during cybersecurity testing, a spokesperson confirmed on Wednesday.
AI #180: No Longer In Charge
What we know about internal AI models hacking into real companies during cyber evaluations keeps getting worse.
Hackers Simply Asked Meta AI to Give Them Access to High-Profile Instagram Accounts. It Worked
The exploit shows the extreme risk of offloading technical support to AI.
AI-powered hacking has exploded into industrial-scale threat, Google says
Criminal groups and state-linked actors appear to be using commercial models to refine and scale up attacks
Hackers hijacked Instagram accounts by tricking Meta AI support chatbot into granting access | TechCrunch
Several users on social media reported having their Instagram accounts hacked over the weekend. Meta's own support chatbot was blamed for allowing hackers to hijack accounts.
OpenAI says AI models went rogue during testing, triggering ‘unprecedented’ breach at startup
OpenAI said that the breakout was “an unprecedented cyber incident, involving state-of-the-art cyber capabilities,” and that it was reinforcing its safeguards.
Anthropic Says Its A.I. Systems Broke Into Computers at 3 Organizations
The disclosure followed OpenAI’s report last week that its own artificial intelligence had hacked into the network of an online library.
Anthropic Says Its A.I. Systems Broke Into Computers at 3 Organizations
The disclosure followed OpenAI’s report last week that its own artificial intelligence had hacked into the network of an online library.
OK, Well, Rogue AI Agents Are Hacking Again
Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving instructions for future bad behavior.
Hackers Used Meta’s AI Support Bot to Seize Instagram Accounts – Krebs on Security
The Instagram accounts for the Obama White House and the Chief Master Sergeant of the U.S. Space Force were briefly defaced with pro-Iranian images and messages over the weekend, after instructions began circulating on Telegram showing how to trick Meta's…
Zack Whittaker (@zackwhittaker@mastodon.social)
Another AI test gone awry, U.K. edition. "An agent tried to insert malicious code into an open-source project. In an attempt to get the code approved, the agent engaged in social engineering — creating fake online identities and using them to pressure the project's maintainer to approve the code." More: https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing
Top AI Security Incidents of 2025 Revealed | Adversa AI
Discover how AI systems are being hacked in the wild — from prompt injection to agent abuse — with real breaches, lessons, and defenses in Adversa AI’s 2025 report.
Why is Meta destroying its engineering organization?
Leadership at the social media giant has been on an AI-fueled rampage through its engineering org. We report what’s happened
How a 40-Minute Window Brought Down a $10 Billion AI Startup: The Mercor Data Breach, Explained
A poisoned open-source package, a credential-stealing payload, and 4 terabytes of stolen data here’s what every AI company needs to learn…
Investigating three real-world incidents in our cybersecurity evaluations
In a review of our cybersecurity evaluation transcripts, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations. Below we describe what happened, how it happened, and what we’re changing. We encourage other AI labs to perform similar reviews.