INSPECTING ARCHIVED INTELLIGENCE (OUTDATED VERSION).

Artex AI Pen-Test Tool Hacked to Steal Azure Key Secrets

| 2026-11-10 21:01 CRITICAL HIGH AI-ENABLED ATTACK DATA BREACH CYBERATTACK (GENERAL)
Executive Summary
AI-generated
Microsoft saw an AI agent move from scanning GitHub for secrets to exfiltrating data from an Azure Key Vault in five minutes, for example. In one case, the AI agent went from searching GitHub to pulling data from Azure Key Vault in only five minutes. In one case, hackers were able to steal credentials and exfiltrate data from Azure Key Vaults and Storage Accounts, as well as abuse Azure AI services.
Technical Mitigations AI-generated
• Reset credentials and API keys that may have been exposed, and review access logs for the affected accounts or integrations.
Technical Observables 4 IoCs Login Required
Indicators of Compromise (IoCs) Protected

Raw threat telemetry, malicious IP addresses, file hashes, and direct VirusTotal correlation are restricted to authenticated users.

ips 4
Intelligence Metadata
Actors / Malware / CVEs / Campaigns
ARTEXARTEXCobalt StrikeCobalt Strike
Target & Sectors
APAC APAC technologytechnology
Incident Timeline
‎around Oct. 10
Threat actors used the Artex framework to launch a massive password-spraying and credential-stuffing campaign against more than 300 specific user accounts at eight critical organizations around Oct. 10, resulting in over 151,000 authentication requests.
victims 300 specific user
general_metric 151,000 authentication requests
‎2026/10/11
Threat actors used the Artex framework to launch a massive password-spraying and credential-stuffing campaign against more than 300 specific user accounts at eight critical organizations.
victims 300 specific user
general_metric 151,000 authentication requests
‎Oct. 29
Threat actors tracked as Vapor Panda used Artex AI to scan GitHub and then steal an Azure Key Vault.
target_region India
tactic Espionage
organisation CrowdStrike
attribution CERT
attribution CERT-In
organisation Censys
general_metric 1,400 exposed console deployments
‎2026/11/03
Microsoft last week published a blog post discussing how a financially motivated Cambodia-based threat cluster tracked as Storm-3358 started using Artex in its attacks against financial organizations primarily (but not exclusively) in…
target_region Cambodia
target_region APAC
organisation Storm-3358
‎Nov. 4
Threat actors tracked as Vapor Panda, linked to financially motivated activities in India, deployed over 1,400 exposed Artex consoles online.
target_region India
tactic Espionage
organisation CrowdStrike
attribution CERT
attribution CERT-In
organisation Censys
general_metric 1,400 exposed console deployments
‎2026/11/09
GitGuardian identified 45 autonomous AI-powered attack frameworks, including Artex, which were capable of conducting attacks autonomously.
organisation GitGuardian
general_metric 45 different attack frameworks
‎2026/11/10
Threat actors used the ARTEX AI framework to scan public GitHub repositories for exposed credentials and API keys, which were then used against cloud accounts.
organisation Microsoft 365
organisation Microsoft
organisation GitHub
organisation Artex & Its Ilk Appeal
organisation CrowdStrike
data_breach 69 GB Government Breach Microsoft
organisation OAuth
organisation Entra ID
organisation Storm-0940
organisation The AI Pen-Test
organisation Akamai
organisation ConnectWise
organisation AWS
organisation Aviatrix
organisation ARTEX AI Azure Key Vault secrets Searching
organisation App Service
victims 200 organizations
‎2026/11/10
That's not to say these tools are inherently bad — pen-testing tools have many legitimate use cases — but it does illustrate the wide range of options for today's attacker.
Tactical Metrics
Metrics
data_breach
69
Gb Government Breach Microsoft
Metrics
victims
300
Specific User
Metrics
infrastructure
‎Microsoft 365
Affected Product
Metrics
victims
200
Organizations