Amazon: China-linked hackers' AI agents found and exploited a zero-day on their own
Autonomous AI agents run by a suspected China-linked threat actor found and exploited a previously unknown vulnerability on their own, Amazon's threat intelligence team says. The operator gave the agents a list of targets and a plain-language goal: "obtain shell access."
Amazon found the campaign on 10 September, when it came across a publicly hosted instance of Cairn, an open source autonomous AI penetration testing framework, running without authentication, so the operator's prompts and the agents' output were visible to anyone. The records showed a roughly 48-hour campaign against universities in East Asia outside mainland China.
Against a server running MONAI Label, an open source tool from the MONAI project for AI-assisted annotation of medical images, the agents mapped the API, found a path traversal flaw in a file upload parameter and, in about 11 minutes, went from mapping the application to writing arbitrary files on the server. In a later session they used the flaw to plant a Python reverse shell and gained a root shell. Amazon assesses with high confidence that the bug was a zero-day, and with moderate confidence that the actor is Chinese-nexus, based on Simplified Chinese prompts, China Standard Time timestamps and the targets.
Other operations, including a 16-hour attempt on an unprotected Redis database and a six-hour attack on a university GPU server, failed, but Amazon says they show the agents kept adapting for nearly a full day without human direction. The MONAI Label developers rate the flaw critical; it affects version 0.8.5 and earlier, and a fix will be in the next release, SecurityWeek reports.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Cybersecurity AI Weekly or Daily AI Brief.
Also, consider following us on social media:
More from Cybersecurity
Nov 20 Army taps OpenAI first to bring AI into Project Gatekeeper software vetting Nov 20 OpenAI says new safeguards cut reasoning-extraction attacks on GPT-6.2 Astra to 0.2% Nov 20 Taylor & Francis retracts paper that hid a prompt telling AI reviewers to praise it Nov 20 GAO says AI magnifies cyberattacks and sets out 16 policy options for AI in cyber defence Nov 20 Dragos seeded two million AI prompts with secrets and found breaches at three providersCybersecurity AI Weekly
Weekly newsletter about AI in Cybersecurity.
Industry analysis
2025 Global Business Services Agenda: Gen AI Takes Center Stage
This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.
Read moreYou may also like
Attackers used an open-source AI hacking agent with GLM and DeepSeek models to breach 10 organisations, Unit 42 finds
FBI warns ARTEX lets attackers automate intrusions at machine speed
Google says hackers now run AI agents to build and launch exploits
Japan's JPCERT/CC finds about 1,000 servers used as bases for AI-driven cyberattacks
Attackers Used 44 AI Agents in CyberStrikeAI Campaign Against Japan
Daily AI Brief: the AI news that matters, in your inbox.