ANALYSIS

Amazon: Hackers' AI Agents Found a Zero-Day in 11 Minutes

Illustration of a glowing AI agent icon rising from a circuit board, representing autonomous AI hacking agents
Amazon says Cairn's AI agents chose every step of the attack after receiving a one-line goal. Source: Santage
Quick answer: On November 20, 2026, Amazon Threat Intelligence reported that a Chinese-nexus actor's AI agents, running on the open-source Cairn framework with the goal "obtain shell access," autonomously discovered a path traversal zero-day in an open-source medical imaging AI application in September 2026. The agents reached arbitrary file write in about 11 minutes and later a root shell, while failing against two hardened university systems after about 16 hours and more than 6 hours of effort.
TLDR

AI hacking agents have crossed from exploiting known flaws to discovering new ones on their own, and the case Amazon published on November 20 shows the decisive gap in AI-era security now sits between the minutes an agent needs to find a bug and the days a project needs to ship the fix.

Cairn agents turned a one-line goal into a root shell

Amazon found the operation by accident. On September 10 its analysts came across a publicly hosted Cairn server left running without authentication, which exposed the operator's prompts, configurations and the agents' own output. The prompts were in Simplified Chinese, scripts used China Standard Time, and the targets were universities in East Asia outside mainland China during a roughly 48-hour campaign starting September 8. Amazon attributes the activity with moderate confidence to a Chinese-nexus actor.

Cairn is an open-source system that coordinates several AI workers toward a goal stated in plain language, and its GitHub page describes it as validated first on autonomous penetration testing. The operator supplied IP addresses and a goal. The agentic AI system chose every step after that.

"In about 11 minutes, the agents went from mapping the application's API to arbitrarily writing files on the server."

Amazon Threat Intelligence, AWS Security Blog, November 20, 2026

In a later session the agents wrote a Python reverse shell into sitecustomize.py, a file Python loads at startup, then called the application's training endpoint to launch a fresh process, which handed them a shell running as root. The operator then stepped in, gave the agents a tunnel into a second university running the same software, and pointed them at the rest of that network.

Bar chart of time Cairn AI agents spent on three targets in September 2026: about 16 hours on a university Redis server, failed; more than 6 hours on a university GPU server, failed; about 11 minutes to exploit a zero-day in a medical imaging AI app
Two hardened servers absorbed more than 22 hours of autonomous effort and held, while the unpatched application fell in 11 minutes. Chart: Santage. Source: Amazon Threat Intelligence, Nov 20, 2026.

Failed operations reveal the agents' persistence

The operations that failed say as much as the one that succeeded. Against a university Redis database open without a password, the agents worked through replication abuse, sandbox escapes, configuration writes and memory corruption, tried Log4Shell on a neighbouring service, mapped the internal Docker network through a server-side request forgery flaw, and sprayed credentials at PostgreSQL and SSH, all across about 16 hours and 148 sequential actions. Against a GPU cluster they first built a list of about 80 real usernames from faculty pages, archived sites and academic papers, then tried more than 30,000 credential combinations over six hours.

By the numbers
~11 minFrom API mapping to arbitrary file write
148Sequential agent actions against one Redis server
30,000+Credential combinations tried on a GPU server
5.7kGitHub stars on the open-source Cairn project

Amazon's own conclusion is about tempo. An agent that finds and exploits a new flaw in minutes finishes before many security teams have triaged the first alert, and one that runs for 16 hours never tires or clocks off. The company recommends high-confidence detections wired to automated response, with people supervising outcomes.

Finding a new bug used to be the slow, expensive step in an attack. Cairn made it the fast one, so the slowest step left in the system is now the defender's release cycle.

The fix existed before the patch did

Amazon does not name the medical imaging software, and says it notified the maintainers, who released a fix and an advisory. A critical GitHub advisory for MONAI Label, the annotation server in the open-source MONAI medical imaging project, matches the description closely. Published on November 18 and noting the flaw was originally reported by an AWS vulnerability disclosure account, the advisory describes a path traversal in datastore upload endpoints that allows arbitrary file writes. It adds that authentication is off by default, so any client that can reach the server can exploit it. The code fix is merged, yet the advisory lists every version up to 0.8.5 as affected, names no patched release, and says the fix will arrive in the next one.

That sequence is the story's real lesson. Discovery took 11 minutes, the advisory came about ten weeks after Amazon saw the attack, and on November 22 users installing from the package index still had no fixed version to download. Santage tracked the same gap in October, when AI-found PHP flaws were exploited four days before the patch. Research AI tools such as MONAI often run on university and hospital networks with default settings, which makes them easy prey for a system that tries every endpoint. Until a release ships, the advisory's workarounds are the practical defence: switch on MONAI Label's authentication setting, keep the server off untrusted networks, and run it as an unprivileged user that can write only to its own datastore.

Date (2026)Primary sourceWhat it documented
Sep 22Gambit SecurityA financially motivated actor ran Cairn with other open-source agents against online retailers
Nov 12Palo Alto Networks Unit 4225 Cairn operations against 19+ organizations, 10 confirmed breaches, run on Zhipu GLM 5.2 and DeepSeek V4
Nov 13Amazon Threat IntelligenceDecoy sensors captured ARTEX agents hunting AI API keys from Oct 3 to Nov 5
Nov 20Amazon Threat IntelligenceCairn agents discover and exploit a zero-day on their own

Source: Gambit Security, Sep 22; Palo Alto Networks Unit 42, Nov 12; Amazon Threat Intelligence, Nov 13 and Nov 20, 2026. Table: Santage.

Open-source attack agents now spread faster than defences

Cairn was built for defenders, and its popularity shows how fast dual-use agent tools travel. Its GitHub repository showed about 5,700 stars and 1,200 forks on November 22, and Unit 42 reported a customized fork driving the espionage operations it tracked, run on open-weights Chinese models. The same week, the European Commission confirmed it had been hit by an AI-generated attack built on ARTEX, and Dragos reported tracking 2 million attacker AI prompts. Unit 42 concluded only ten days earlier that autonomy was raising the volume and reach of attacks while the exploits themselves stayed simple. Amazon's case moves that line, because finding a previously unknown flaw is exactly the kind of skilled work the agents were assumed to lack. The common thread is a multi-agent system that needs only a target and a sentence.

Spin the Cairn campaign wheel
Spin to land on one number from the AI agent campaigns documented this autumn.
Quick quiz
How long did Cairn's agents need to go from mapping the medical app's API to writing files on its server?
Reader poll
Should open-source autonomous hacking agents like Cairn be restricted?

Hardened systems held against 22 hours of tireless machine effort, which is the encouraging half of Amazon's report. The worrying half is that an unpatched application with default settings lasted 11 minutes, and the fix for it was still waiting for a release more than two months later. Defenders who want to keep pace with autonomous attackers will have to ship patches, and switch on authentication, at something closer to machine speed.

Santage is committed to independent, transparent journalism. This article is produced in accordance with Santage's Editorial Standards and aims to provide accurate and timely information. Readers are encouraged to verify information independently.