AI agents are hacking systems — but it's not a robot uprising

Full text

Artificial intelligence (AI) has been making headlines for all the wrong reasons in recent weeks.

In July, OpenAI revealed that one of its experimental AI agents attacked publicly accessible services, including the AI hosting platform Hugging Face , during internal security testing. Then, Anthropic disclosed that Claude had independently chained together exploits against real software and developed new techniques for finding weaknesses in code. Shortly afterward, Meta confirmed that one of its own AI models breached another organization's systems during an evaluation after a misconfiguration gave it internet access.

They're separate incidents, but together they raise a bigger question: Has AI suddenly become capable of hacking? The short answer is yes — but probably not in the way the headlines suggest.

None of these incidents involved an AI model deciding on its own to attack random targets. Instead, researchers gave the models realistic tools, internet access, or vulnerable systems to see how well they could perform offensive cybersecurity tasks. What surprised many experts wasn't that the models tried to hack systems but how capable they proved to be once given the opportunity.

Why are there suddenly so many AI hacking stories in the news?

Several things have changed at once. The most obvious is that today's AI models are simply better than the chatbots people were using even a year ago. Instead of only answering questions, many frontier models can now write code, execute commands, browse the web, use external software tools and repeatedly refine their own work until they achieve a goal.

At the same time, AI companies have become much more willing to test those capabilities and reveal the results. Rather than keeping security evaluations behind closed doors, firms including OpenAI, Anthropic and Meta are publishing reports describing what happened when their newest systems were challenged by professional "red teams" — security experts tasked with deliberately finding weaknesses or ways to misuse a system.

"We are witnessing a perfect storm of capability and aggressive testing," Dray Agha , senior manager of security operations at Huntress, a cybersecurity company specializing in managed threat detection and response, told Live Science. "The sheer volume of software flaws being discovered in 2026 has already roughly doubled compared to 2025, largely driven by AI systems. Tech giants are actively deploying these models internally to stress-test their own infrastructure, leading to rapid, high-profile discoveries of vulnerabilities."

Antonino Vaccaro , professor of business ethics at IESE Business School and director of its Observatory for AI Ethics in Organizations, agrees both factors are contributing to the recent spate of high-profile hacking stories.

"The first, and probably most important, is the rapid evolution of AI systems," he told Live Science. "Every second they increase their capabilities, information, resources and connections with other online tools." At the same time, governments and the AI industry are investing more heavily in testing and oversight as concerns around accountability continue to grow, he added.

Can AI really hack computers by itself?

Not exactly. Many headlines have described AI "escaping" test environments or acting autonomously. But experts said those descriptions can easily give the wrong impression.

"We need to be wary with the meaning of the adjective 'autonomous' when associated with AI systems," Vaccaro said. Unlike humans, he continued, AI models don't form intentions or make independent decisions about what they want to do. Instead, they follow objectives set by developers or users, sometimes producing results that surprise the people who built them.

Agha noted that these AI models are simply working to achieve a set objective. "The public should view these incidents as software optimization gone wrong, not as the dawn of a malicious, self-aware AI," he said. "It's less 'Terminator' and more like a very capable, literal-minded intern who breaks the law to finish a spreadsheet faster."

The game-changer is the shift from conversational models to agentic models.

Dray Agha, senior manager of security operations at Huntress

In all three recent cases, the AI models didn't operate without supervision. Researchers had deliberately given them the necessary tools and conditions to see what they could do. Meta's incident, meanwhile, stemmed from a misconfigured testing environment rather than the model independently breaking out of its digital sandbox.

The concern isn't that AI has become self-aware. It's that these systems are becoming increasingly effective at carrying out complicated technical tasks when given the right permissions.

Why are the very newest AI models better at cybersecurity?

The biggest change is the rise of so-called "agentic" AI. Conventional chatbots generated text one response at a time. Agentic systems, however, can plan a series of actions, decide what to do next, use software tools, test their own ideas and keep working toward a goal without requiring constant human input. That makes them surprisingly effective assistants for cybersecurity research.

"The game-changer is the shift from conversational models to agentic models," Agha said. "Today's frontier AI doesn't just answer questions. It can autonomously chain together actions, write code, use command-line tools, and iterate on its own failures."

Giving AI direct access to development environments also allows it to test whether its own ideas actually work. Instead of suggesting a possible software bug, it can often write proof-of-concept code, modify it if it fails and try again.

The same capabilities aren't limited to attackers. Security teams are already using AI to review code for bugs, analyze suspicious files, and speed up investigations that would otherwise take analysts hours.

Should people be worried about AI committing cyberattacks?

Experts said AI's role in cyberattacks should be a cause for concern, but for different reasons than science fiction would suggest.

The most immediate risk isn't AI deciding to launch attacks on its own, but cybercriminals using AI to commit familiar cybercrimes much faster than before.

Criminals don't need AI to invent entirely new ways of attacking people. Instead, these models can speed up existing attack methods. It can sift through huge amounts of public information about potential victims, help write more convincing phishing emails, identify software weaknesses and generate code that attackers can adapt for their own use.

"The threat is human malice, supercharged by AI scale and speed, not autonomous AI deciding to go rogue," Agha said.

Vaccaro believes that growing capability also creates a growing responsibility. "We have a new disruptive technology that needs to be regulated and controlled," he said, arguing that governments, companies and researchers all have a role to play in ensuring increasingly capable AI systems remain subject to meaningful oversight.

How will AI change cyberattacks in the future?

The recent disclosures are unlikely to be the last. As AI companies race to build more capable systems, they are also giving those systems access to more tools, more computing resources and more realistic testing environments. That makes future evaluations more likely to uncover new — and occasionally alarming — behaviors.

Related stories

AI self-replication hacks 'no longer purely theoretical,' study finds —‬ ‪but experts say it's too soon to panic

'I violated every principle I was given': AI agent deletes company's entire database in 9 seconds, then confesses

'You can't patch your way out of it': Cheap AI worm can spread between devices without human guidance — but how did scientists create it?

Most experts expect AI to become an increasingly powerful cybersecurity assistant rather than an independent cybercriminal. It will probably find software bugs faster, help defenders respond to attacks more quickly, and automate many routine security tasks. At the same time, criminals will use the same technology to improve phishing campaigns, accelerate vulnerability research and make attacks more convincing.

The next wave of AI security headlines is unlikely to be about machines plotting against humanity: It will instead likely be about increasingly capable software doing exactly what it has been asked to do — and showing just how much that capability has grown.