
Hackers Hire AI Agents as Interns, Ask Them to Break Things at Machine Speed
Ourtake
The intern who never sleeps has also learned to read security patches for fun.
What happened
Google's Threat Intelligence Group reported that threat actors are using autonomous multi-agent offensive frameworks such as ARTEX, CAIRN, CyberStrikeAI and PentAGI to run multi-stage intrusions and reverse-engineer software patches into exploits. The report also describes LLM-driven phishing tooling like the Jieyou platform and LLMjacking, where stolen LLM access is resold through underground proxies.
Sources
- thehackernews.com · Google Finds Hackers Using AI Agents to Build and Run Exploits From Software Patches (opens in a new tab)
- securityaffairs.com · Google GTIG Warns AI Agents Automate Exploits, Steal Credentials and Scale Cybercrime (opens in a new tab)
- helpnetsecurity.com · Google finds AI agent writing and launching exploits with no human in the loop - Help Net Security (opens in a new tab)
- therecord.media · Chinese state group developing automated attack tool for cyber espionage, Google says (opens in a new tab)