Security/ ai agents · cybersecurity · llm evaluation · ai research

AI Hacking Agents Still Fumble Credential Theft, Study Finds

A new study finds AI agents used for simulated hacking stall on credential theft and lateral movement, and their own validators overrate success.

Six frontier AI models tried to hack their way through simulated corporate networks - and mostly stalled out well before pulling off a clean breach.

Researchers built an "Autonomous Adversary" system that pairs an orchestrating LLM with executor and validator LLMs, then ran six top models through two enterprise-like lateral-movement scenarios under three setups: fully scripted instructions, agents scaffolding their own tools, and fully autonomous operation. Instead of just counting wins, the team tracked token spend, retry counts, and runtime, then had a separate LLM act as judge to flag planning problems like mismatched tool choices, repetitive strategies, over-specified steps, and weak recovery after a dead end. The validator LLMs responsible for grading success were generally relevant and grounded in real evidence, but often vague and too quick to call a stalled attempt a win. The worst slowdowns clustered around credential theft and lateral movement, and got more pronounced as scenarios grew more complex or agents were handed more autonomy.

This is a useful corrective to the breathless "AI can hack now" narrative that follows every red-team demo. The paper's real finding isn't whether an agent eventually breaks in - it's how much it flails, retries, and gets falsely told it succeeded along the way, details a simple pass-fail scoreboard would never surface. That distinction is what security teams actually need when deciding how seriously to take autonomous attack tooling.

A model that occasionally stumbles into a credential cache is a real risk. A model whose own judge keeps grading half-finished break-ins as successes is a different, and arguably more urgent, problem to fix first.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →