Skip to content

Topic

Agentic AI Attacks

Cyberattacks in which autonomous AI agents chain intrusion steps—exploitation, credential theft, lateral movement, exfiltration—without human direction.

Current stories

securityConfirmed6 publishers

Storm-3168 mapped an Azure tenant for 17 hours before a seven-minute deletion run

Microsoft says Storm-3168, also tracked as JADEPUFFER, used two stolen Azure service principals to try deleting more than 100 storage accounts. The deletions took about seven minutes, so the 17 hours of API reads before them were when anyone watching those identities had time to act.

Perspective Coverage

6 publishers
Builder
Builder 23%
Operator
Operator 70%
Investor
Investor 7%

Reality

Evidence72
Adoption
Not scored
Hype gap+25
Incentives55
Confidence70
buildOne report1 publisher

DIVD says an AI agent chained two Zammad zero-days to root on its helpdesk host

DIVD says an attacker chained two unpublished Zammad bugs from an unauthenticated web session to root on its helpdesk host. Its claim that an autonomous AI agent did it is still a first-party assessment with no independent confirmation yet.

Publishers:dev.to

Reality

Evidence55
Adoption35
Hype gap+30
Incentives55
Confidence55
securityOne report1 publisher

A GDPR breach filing in Spain credits the entire intrusion to an LLM agent

The organization that filed it told the AEPD that the agent searched for flaws, logged in, kept hunting bugs inside the application and then altered personal data and opened invoices, and the regulator has not yet investigated.

Reality

Evidence38
Adoption20
Hype gap+32
Incentives55
Confidence45
buildOne report1 publisher

Exploit development for PaperCut took under four hours from an empty workspace

GreyNoise says a likely Russian-speaking actor built and tested PaperCut exploits in a lab, then ran hundreds of agents on a Codex harness with a DeepSeek model against 440 servers in 48 countries. The sending infrastructure was already on its watchlist.

Publishers:greynoise.io

Reality

Evidence58
Adoption70
Hype gap+12
Incentives68
Confidence55
securityConfirmed3 publishers

Attacker agents ran a mass credential harvest from inside the victim's own cloud in six hours

Mandiant traced the Q2 2026 campaign to an AI coding chatbot, one prompt and a set of agent instructions that ran the scanning pipeline, fixed its own errors and rotated IPs with nobody at the keyboard.

Perspective Coverage

3 publishers
Builder
Builder 30%
Operator
Operator 57%
Investor
Investor 13%

Reality

Evidence58
Adoption62
Hype gap+24
Incentives70
Confidence66