INSPECTING ARCHIVED INTELLIGENCE (OUTDATED VERSION).
Attackers are using AI agents to automate cybercrime at 'industrial scale,' FBI and AWS
|
2026-11-16 19:52
HIGH
HIGH
AI-ENABLED ATTACK · AUTONOMOUS
CYBERATTACK (GENERAL)
Executive Summary
AI-generated
Between October 3 and November 5, Amazon’s MadPot honeypot threat sensors detected two ARTEX campaigns: one that allowed thieves to steal AI credentials at “industrial scale” to gain free access to models, and a second that generated deepfake videos to trick live selfie checks. Between 3 October and 5 November, Amazon’s MadPot network of decoy sensors caught requests from ARTEX agents. Attackers' AI agents have been hunting for weak spots in internet-exposed AI apps such as LiteLLM, One API, and Dify to steal the AI provider keys stored inside, according to the agents' own records.
Intelligence Metadata
Actors / Malware / CVEs / Campaigns
CVE-2026-28797CVE-2026-28797
CVE-2025-3248CVE-2025-3248
Target & Sectors
Global Scope
energyenergy
technologytechnology
financefinance
healthhealth
Incident Timeline
Between 3 October and
Between 3 October and 5 November, Amazon's MadPot network of decoy sensors caught requests from ARTEX agents.
October 3 to late last week
Attackers used AI agents to automate cybercrime at an industrial scale, sending requests that often carried a campaign's full history from October 3 to late last week.
5 November
Between 3 October and 5 November, Amazon's MadPot network of decoy sensors caught requests from ARTEX agents.
2026/11/09
Attackers used AI agent ARTEX for GitHub secret hunting, targeting exposed credentials including API keys for AI inference.
Click on any entity below to view its context and source!
organisation
Microsoft
Microsoft reported last week that attackers were using agentic AI tools such as ARTEX for
GitHub secret hunting
, looking for exposed credentials that included API keys for AI inference.
2026/11/16
Attackers are using the open-source AI penetration testing framework ARTEX to automate their attacks on banks, governments, energy and healthcare providers, and other critical sectors around the globe.
Click on any entity below to view its context and source!
organisation
AWS
Attackers are using AI agents to automate cybercrime at 'industrial scale,' FBI and AWS warn.
Amazon informed the AWS customers it believed were affected by these campaigns.
organisation
Ollama
The targets included API gateways and proxies such as One API, New API, Veloera, Sub2API and LiteLLM, as well as AI development platforms such as Dify, FastGPT, Langflow, RAGFlow, Open WebUI, LobeChat and Ollama.
Targets named in the records include LLM gateways and proxies such as One API, New API, Veloera, Sub2API and LiteLLM, and AI app builders such as Dify, FastGPT, Langflow, RAGFlow, Open WebUI, LobeChat and Ollama.
organisation
PyPI
Those included GitHub repositories and event archives, where secrets sat outside automated revocation, plus npm and PyPI packages, container layers, notebooks, model-hosting spaces, paste sites and Telegram channels.
To find leaked keys, the agents used internet scanning services and certificate transparency logs, and searched GitHub repositories and event archives, npm and PyPI packages, container image layers, notebooks, model-hosting spaces, paste sites, and Telegram channels.
organisation
Telegram
Those included GitHub repositories and event archives, where secrets sat outside automated revocation, plus npm and PyPI packages, container layers, notebooks, model-hosting spaces, paste sites and Telegram channels.
To find leaked keys, the agents used internet scanning services and certificate transparency logs, and searched GitHub repositories and event archives, npm and PyPI packages, container image layers, notebooks, model-hosting spaces, paste sites, and Telegram channels.
organisation
ConnectWise Cloud Backup
The FBI also highlighted a September ARTEX campaign that targetedd ConnectWise Cloud Backup customers in a supply chain attack that ultimately compromised more than
2,250 downstream Microsoft tenants
.
organisation
Microsoft
The FBI also highlighted a September ARTEX campaign that targetedd ConnectWise Cloud Backup customers in a supply chain attack that ultimately compromised more than
2,250 downstream Microsoft tenants
.
organisation
Amazon
The records, which Amazon's threat intelligence team captured with decoy servers, describe stolen keys being used to run the AI models that powered the search for more keys.
organisation
Moses
This video achieved 11.5 frames per second, which Moses said is “close to what a live video check expects.”
organisation
ConnectWise
The alert's examples include an
earlier campaign
against South Korean financial institutions that stole personal information on about 67,000 people, and the
ConnectWise compromise
.
organisation
GitHub
After these security breaches became public, the original ARTEX developer removed the GitHub repository in October.
infrastructure
1.3.0
Here is the status of the flaws named in the playbook:
Product
Flaw
Status
Langflow
CVE-2025-3248, missing authentication that lets a remote attacker run code
Versions before 1.3.0 are affected, and 1.3.0 is the fixed version (
release notes
).
organisation
Scale Their Attacks
ARTEX: How Cybercriminals Use AI Agents to Scale Their Attacks.
organisation
MadPot
“The ARTEX agents sent these requests to MadPot sensors configured to present as popular large language model (LLM) inference APIs, and the requests carried the agents’ own records of their campaigns.”
reads the report
.
organisation
Operators
Operators set the mission and left the rest to the agents.
organisation
IT Information Security
…tals right remains the most effective defense.”
Follow me on Twitter:
@securityaffairs
and
Facebook
and
Mastodon
Pierluigi Paganini
(
SecurityAffairs
– hacking, ARTEX)
facebook
linkedin
twitter
AI
ARTEX
Artificial Intelligence
Hacking
hacking news
information security news
IT Information Security
Pierluigi Paganini
Security Affairs
Security News
organisation
Amazon Uncovers AI
Amazon Uncovers AI Agent Campaign Targeting LiteLLM, Dify, and Other Apps for API Keys.
organisation
Cloudflare
In a separate case reported this week, Cloudflare's incident responders saw ARTEX gain access to a compromised API token that had been used for CI/CD.
organisation
Cisco Talos
Check logs for the 11 IP addresses published with the decoy findings, and for the more than 2,500 addresses that researchers at Cisco Talos link to ARTEX in their
indicator files
.
infrastructure
11 IP addresses
Check logs for the 11 IP addresses published with the decoy findings, and for the more than 2,500 addresses that researchers at Cisco Talos link to ARTEX in their
indicator files
.
organisation
Snort 2
The researchers'
detection rules
for ARTEX are Snort 3 rules 7:76, 7:77 and 7:78, and Snort 2 rules 1:67494, 1:67495 and 1:67496.
November 16, 2026
Threat actors used AI agents to automate cybercrime at an industrial scale, with Amazon detecting the agents running on ARTEX stealing AI credentials and testing deepfake ID bypasses.
Click on any entity below to view its context and source!
industry
Finance
General Document Context
industry
Health
General Document Context
industry
Energy
General Document Context
industry
Technology
General Document Context
organisation
Amazon
ARTEX: How Cybercriminals Use AI Agents to Scale Their Attacks
Pierluigi Paganini
November 16, 2026
Amazon spotted AI agents running on ARTEX steal AI credentials and test deepfake ID bypasses.
Tactical Metrics
Metrics
infrastructure
1,465
Hosts
Click for context!
However, forked and localized variations plus a commercial version remain, and as of November 4 internet scanning service Censys
identified 1,465
hosts running an exposed ARTEX console.
Metrics
infrastructure
1.3.0
Software Version
Here is the status of the flaws named in the playbook:
Product
Flaw
Status
Langflow
CVE-2025-3248, missing authentication that lets a remote attacker run code
Versions before 1.3.0 are affected, and 1.3.0 is the fixed version (
release notes
).
Metrics
infrastructure
0.25.0
Software Version
Version 0.25.0, released on April 21, renders templates in the sandbox the advisory recommends, according to its
SSTI fix notes
.
Metrics
infrastructure
11
Ip Addresses
Check logs for the 11 IP addresses published with the decoy findings, and for the more than 2,500 addresses that researchers at Cisco Talos link to ARTEX in their
indicator files
.
Intelligence Sources
The Hacker News
2026-11-16
Security Affairs
2026-11-16
ARTEX: How Cybercriminals Use AI Agents to Scale Their Attacks
Security Affairs
The Register - Cybercrime
2026-11-16
Attackers are using AI agents to automate cybercrime at 'industrial scale,' FBI and AWS warn
The Register - Cybercrime
Unpublish from Social Media?
Are you sure you want to delete this podcast video from all synchronized social networks (YouTube, Facebook, Threads)?
Important:
Due to Meta API restrictions, Instagram Reels cannot be deleted automatically via API by third-party apps.
View Profile to Delete Manually
View Profile to Delete Manually
Tactical Intelligence
Report Intelligence Issue
Podcast Options
Generate
Incident Version History
CURRENT VERSION
Last Updated: 2026-11-17T07:44
Comprehensive Tactical Telemetry
Highly Correlated Entities
20x
organisation
Identified Entity
AWS
entity
13x
timeline
Temporal Reference
Between October 3 and November 5
date
4x
industry
Targeted Sector
Finance
sector
4x
tactic
MITRE ATT&CK Technique
T1059.007 - JavaScript
technique
2x
attribution
Attributing Entity
FBI
authority
2x
vulnerability
Exploited CVE
CVE-2025-3248
cve
2x
infrastructure
Software Version
1.3.0
version
2x
general metric
Rules
3
rules
Contextual Telemetry
Context Block
13 METRICS
general metric
Frames
12
frames
target region
Target Country
Korea, Republic of
country
general metric
People
67,000
people
general metric
Attack
2,250
attack
infrastructure
Hosts
1,465
hosts
general metric
Pixels
7
pixels
source region
Origin Country
China
country
tactic
Cyber Operation Type
Ransomware
tactic
infrastructure
Ip Addresses
11
ip addresses
general metric
Addresses
2,500
addresses
general metric
Dump Requests
400
dump requests
general metric
Requests
69
requests
general metric
Families
50
families
Click on any entity below to view its context in the main text!
Selective Unpublish
Select the networks you want to remove this post from. The system will try to delete the real post through the API and clean the database so you can publish it again.
By navigating this website, you accept the use of strictly necessary technical cookies for session security and basic platform functionality. We do not use tracking or advertising cookies. Read our Privacy Policy.
Generating report…
0s