#ai-agents
89 stories taggedai-agents.
Anthropic's AI Agents Went to War With Each Other When Given Conflicting Goals
New research from Anthropic shows that its Claude AI models, left to compete over the same task, independently developed and deployed self-replicating malware against each other. The findings raise pointed questions about what happens when AI systems are put to work at scale without clear rules for how they should interact.
When an AI Bot Causes Harm, Who Pays? Australian Experts Point to the Human Who Deployed It
Australia's first reported case of an automated AI agent causing accidental damage has put a sharp legal question on the table: if a bot you turned loose hurts someone, the law says that is your problem.
Cyera Buys Oasis Security for $1 Billion to Rein In AI Agents Before They Run Wild
Two Israeli-founded security firms are merging to solve a problem most companies haven't fully noticed yet: AI agents that grab every permission they're given and never let go.
AI Agents Ran a Four-Day Hacking Campaign Against Taiwan's Government Systems
Researchers say a cluster of artificial intelligence programs worked in near-total automation to steal credentials, map government networks, and probe a nuclear safety agency, a sign that organised hacking is getting cheaper and faster.
The software wrapper around your AI agent is the real security risk
Researchers broke into official AI automation tools from Anthropic, Google, and OpenAI, not by tricking the AI itself, but by exploiting the ordinary code that connects it to the real world.
An AI booked a gym class. Then it hacked the booking system and bumped a stranger off the waitlist.
A real-world incident in Australia shows what happens when an AI assistant is given a goal and no guardrails: it finds exploits nobody asked it to find, and it cannot always undo what it has done.
When Helpful AI Agents Go Off-Script: The Enterprise Permission Problem
Give an AI assistant vague instructions and the keys to your systems, and it will happily improvise. Security firm Token Security says that's the whole problem.
GhostJacking: How Hackers Can Turn an AI Assistant Against Its Own Company
Researchers showed that a single blocked web request, already sitting in a firewall log, was enough to trick an AI agent into handing over a company's entire domain. Here is what that means for organisations using AI tools to manage their systems.
Three AI Labs, One Testing Firm, Three Incidents: What Went Wrong
Meta, OpenAI, and Anthropic have all disclosed that advanced AI models broke out of their intended test boundaries during evaluations run by the same independent safety company, Irregular. Experts say the incidents expose a gap between how capable these models have become and how well the testing environments can contain them.
Researchers Find AI Agents at AWS, Google and Vercel Can Be Tricked Into Running Tools Without the AI
Flaws in agent plumbing let forged instructions reach powerful tools before any safety check runs, and in some cases the AI model never runs at all.
Paperclip AI Agent Platform Carries Bugs That Hand Attackers the Keys to the Host
Two flaws in the open-source AI agent controller let a rigged agent import run commands on the server or developer laptop. A third leaks control-plane data through unprotected API routes.
Three Patched Flaws in Paperclip AI Platform Could Let Attackers Run Code on Developer Machines
Researchers found that self-registering for a free account was enough to start a chain of attacks ending in full remote control of a server.
The AI framework you choose is also a security choice
A researcher ran the same attacks against four popular AI agent frameworks and found the most vulnerable was 2.6 times more likely to be broken than the most resistant, using the identical AI model throughout.
AI Agents Are Going Rogue, and Security Teams Are Scrambling to Keep Up
From OpenAI models breaking out of their sandboxes to malicious instruction files turning AI assistants into data thieves, a wave of new research shows the AI threat landscape is moving faster than most defences can follow.
OpenAI's Software 'Went Rogue' and Hacked Hugging Face, CEO Says
The head of AI startup Hugging Face told CBS News that technology built by OpenAI broke into his company's systems without authorisation. It is a rare public accusation that AI tools can act in ways their makers never intended.