TechBroz · techbroz.com64 incidents on record · updated as they happen
← Hall of Shame

Rank #3 of 64·Security·16 Nov 2026·exploit_agent, an attacker-built multi-agent framework using frontier and local LLMs

Google caught an AI agent turning security patches into working exploits, left on the attackers' own exposed server

Server racks and cabling in a data centre, for illustration; not the attackers' server (edited).
Server racks and cabling in a data centre, for illustration; not the attackers' server (edited). Photo: Gregory Rocher, CC BY 4.0, via Wikimedia Commons; cropped, text overlaid.

“It never sleeps, never eats, and never locked its own server.”

Incident reportSecurityAn exposed attacker staging server; targets were French media, entertainment and education websites
Agent / toolexploit_agent, an attacker-built multi-agent framework using frontier and local LLMs
CompanyUnnamed attacker (suspected Russian-speaking); reported by Google Threat Intelligence Group
DamageStolen victim data found next to an exploit agent that needs no human
Time to detectFound by Google during the quarter; published 16 Nov 2026
StatusVerified: Google's own threat report plus several security outlets; victims and operator not named
Chaos7.0 / 10
  • exploit_agent diffs web-app code before and after each patch
  • It drafts exploits and runs them with no human in the loop
  • Google calls it the first fully automated pipeline of its kind it has seen
  • The exposed server also held stolen victim data
  • Scripts for recon, brute-forcing and installing webshells sat alongside it
  • Targets: French media, entertainment and education websites

Attackers built an AI agent that reads security patches, works out what they fixed and attacks the hole before anyone updates. Then they left it sitting on an exposed staging server, where Google's threat hunters found it.

What happened

Google Threat Intelligence Group says the framework, which its operator called exploit_agent, plugs into several frontier and local AI models. It keeps watching popular web application software, compares the code before and after each patch announcement, works out which flaw was fixed, drafts an exploit and runs it, with no human in the loop. Google says this is the first time it has seen attackers fully automate both finding and exploiting bugs this way. One example in the report shows the agent picking apart the access checks in a WordPress plugin. A config file carried a Russian comment telling the operator to type the AI keys in right there, "not in the chat".

The damage

This was not a lab demo. The same server held data stolen from victims, plus scripts for internal reconnaissance, brute-forcing, installing webshells and even removing other attackers' webshells. Victim telemetry on the box points to French websites in media, entertainment and education. Google names no victims, no victim count and no group, only a suspected Russian-speaking operator.

How it was caught, and what happened next

Google published the find on 16 November in its quarterly AI Threat Tracker, next to other agent-driven attack frameworks it is following. Its warning for defenders: AI is shrinking the window between a patch going public and an exploit arriving.

Lesson for builders

Once a patch is public, assume an agent is already diffing it. Patch internet-facing web apps in hours, not weeks, and hunt for webshells.

Fail card: Google caught an AI agent turning security patches into working exploits, left on the attackers' own exposed server
The fail card

This story in one shareable card. Tap to open it full size.

Share on X All fail cards →

More fails

Get TechBroz Weekly free → All 64 fails