Microsoft Threat Intelligence - ARTEX agents mining GitHub secrets into Entra & Azure Key Vault
Microsoft Threat Intelligence (Nov 5, 2026) reports unattributed cloud-credential harvesting campaign using ARTEX autonomous agent framework. Attackers conduct mass GitHub secret searches querying…
What happened
Microsoft Threat Intelligence (Nov 5, 2026) reports unattributed cloud-credential harvesting campaign using ARTEX autonomous agent framework. Attackers conduct mass GitHub secret searches querying organization names, cloud keywords (Azure, AWS, Entra, Key Vault), and AI provider keys. ARTEX agents authenticate as compromised Azure Entra service principals, then autonomously enumerate and exfiltrate Azure Key Vault secrets, storage account keys, App Service configuration settings, AKS cluster credentials, SharePoint/OneDrive files, Microsoft Graph queries, Azure AI Studio keys, and Azure Foundry credentials within approximately 5 minutes per compromised tenant. Agents feature adaptive retry logic that automatically corrects Azure Resource Manager API version errors on failed calls, demonstrating autonomous error recovery. Campaign operates from IPs 199.19.77.84, Tor exit 199.19.77.18, 65.87.223.26, and 157.22.126.128. Microsoft notes median dwell time of 8 minutes from initial service principal authentication to complete key-vault enumeration, indicating highly automated credential-harvesting workflow targeting cloud and AI infrastructure. VulnCheck (Patrick Garrity, Nov 8, 2026) reports 199.19.77.84 hit VulnCheck canaries Nov 7 exploiting CVE-2025-3248 (Langflow /api/v1/validate/code endpoint). Agent staged Python using @exec decorator, _lf_probe() wrapper function, and |RAISE| exception-based exfiltration channel; dumped env/.env files and langflow.db; checked Docker socket and cloud metadata endpoint 169.254.169.254; grepped for sk-, AIza, AKIA key patterns; read mem0 configuration; decrypted Langflow Fernet-encrypted variables. Linked to Microsoft campaign via shared IP 199.19.77.84; vendor-asserted AI involvement (VulnCheck notes network traffic alone cannot definitively prove agent autonomy).
Threat actors use ARTEX autonomous agent framework to mass-query GitHub for exposed credentials, authenticate as Azure Entra service principals, and autonomously enumerate and exfiltrate Azure Key Vault secrets, storage keys, App Service settings, AKS credentials, SharePoint/OneDrive data, and Azure AI/Foundry keys within minutes
How it happened
Read the flow as text & sources
A catalog reconstruction of the supplied source account. Unknown steps remain explicit; an edge describes the reported relationship between steps.
- 01 · Mass GitHub secret queries
Mass GitHub secret queries
Source for step 1 - 02 · Harvest Azure service principal credentials
Harvest Azure service principal credentials
Source for step 2 - 03 · Authenticate as Entra service principal
Authenticate as Entra service principal
Source for step 3 - 04 · Enumerate Azure Key Vault secrets
Enumerate Azure Key Vault secrets
Source for step 4 - 05 · Exfiltrate storage account keys
Exfiltrate storage account keys
Source for step 5 - 06 · Steal AKS cluster credentials
Steal AKS cluster credentials
Source for step 6 - 07 · Harvest Azure AI/Foundry keys
Harvest Azure AI/Foundry keys
Source for step 7
Why it matters
Reported entry point: Exposed credentials in public GitHub repositories; compromised Azure Entra service principal credentials. Reported impact: Harvest Azure AI/Foundry keys; reported targets include Organizations with exposed Azure service principal credentials on GitHub; targets include AI/ML development teams, cloud infrastructure operators, and enterprises using Azure AI Studio / Foundry; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.
What you can do
Protection & prevention
Scan public repositories for accidentally committed Azure credentials; implement Azure AD Conditional Access policies requiring managed device or IP restrictions for service principals; enable Azure Key Vault firewall and private endpoints; activate Microsoft Defender for Cloud Apps for anomalous Graph API usage; rotate service principal secrets regularly; use managed identities instead of service principal passwords where possible; monitor for rapid sequential ARM API calls and Key Vault enumeration patterns; implement Azure Sentinel detections for service principal authentication from Tor exits or VPN/proxy infrastructure
Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.
Technical detailsTooling, impact & MITRE ATLAS
Attack context
- AI's role
- AI as operator
- Offensive frameworks
- ARTEX
- Additional role
- AI credential theft
- Initial access
- Exposed credentials in public GitHub repositories; compromised Azure Entra service principal credentials
Tooling as reported
AI products, models and artifacts
- ARTEX autonomous agent framework (https://github.com/RuoJi6/ARTEX)Community-maintained fork; the original repository is unavailable.
- LLM-driven Azure API enumeration with adaptive retry
- Langflow (https://github.com/langflow-ai/langflow) - targeted for credential theft via CVE-2025-3248
Other tooling
- GitHub API for secret search
- Azure Resource Manager API
- Microsoft Graph API
- Tor network for anonymization
Targets and reported impact
- Targets / sectors
- Organizations with exposed Azure service principal credentials on GitHub; targets include AI/ML development teams, cloud infrastructure operators, and enterprises using Azure AI Studio / Foundry
- Reported scale / exposure
- Active Nov 2026; median 8-minute dwell time from service principal authentication to complete Key Vault enumeration; ~5 minutes per tenant for full credential exfiltration; campaign IPs observed across multiple tenants
- Target geography
- Multiple regions
Reported attribution
Unattributed activity cluster; Microsoft Threat Intelligence notes related infrastructure observed by Todyl; cloud and AI credential harvesting for follow-on cybercrime operations
Structured attribution
- Actor
- Unknown (ARTEX cloud-secrets cluster)
- Country
- Unknown
- Motivation
- cybercrime
- Attributed by
- Microsoft Threat Intelligence
- Attribution confidence
- low
Detection rules
- Package Runtime Secret File Access Followed by IMDS RequestELASTICView rule
Detects IMDS 169.254.169.254 access and Docker socket enumeration patterns
- Azure Key Vault and credential enumerationGUIDANCE
Monitor Azure Resource Manager API calls from compromised service principals; detect Key Vault secret enumeration; alert on storage account key access; monitor AKS credential retrieval; detect Azure AI Studio and Foundry key access
- Langflow CVE-2025-3248 exploitationGUIDANCE
Monitor /api/v1/validate/code endpoint POST requests; detect @exec decorator usage; alert on _lf_probe() wrapper functions; detect |RAISE| exception-based exfiltration; monitor Fernet decryption attempts
Activity timeline
- First seen
- 2026-11-01
- Last updated
- 2026-11-08
Updates
- 2026-11-05 — Microsoft Threat Intelligence
Microsoft reports ARTEX-based campaign harvesting GitHub-exposed Azure credentials and autonomously enumerating Key Vault, storage, AKS, AI/Foundry secrets within ~5 minutes per tenant; campaign IPs 199.19.77.84, 199.19.77.18, 65.87.223.26, 157.22.126.128
- 2026-11-08 — VulnCheck
VulnCheck reports 199.19.77.84 exploited CVE-2025-3248 (Langflow /api/v1/validate/code) against canaries Nov 7; agent staged Python with @exec, _lf_probe() wrapper, |RAISE| exfil channel; dumped env/.env, langflow.db; checked Docker socket and 169.254.169.254; grepped sk-, AIza, AKIA patterns; decrypted Fernet variables; linked to Microsoft campaign via shared IP
Source defensive notes
Scan public repositories for accidentally committed Azure credentials; implement Azure AD Conditional Access policies requiring managed device or IP restrictions for service principals; enable Azure Key Vault firewall and private endpoints; activate Microsoft Defender for Cloud Apps for anomalous Graph API usage; rotate service principal secrets regularly; use managed identities instead of service principal passwords where possible; monitor for rapid sequential ARM API calls and Key Vault enumeration patterns; implement Azure Sentinel detections for service principal authentication from Tor exits or VPN/proxy infrastructure
MITRE ATLAS
AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.
Adversaries deploy ARTEX autonomous AI agent to automatically discover exposed cloud credentials, authenticate to Azure, and systematically exfiltrate Key Vault secrets and Azure AI service keys Source
Agent autonomously exploits CVE-2025-3248 in Langflow to steal API keys and credentials Source
Agent targets AI platform credentials including Langflow Fernet-encrypted variables and mem0 configuration Source
Indicators of compromise
domains
ips
199.19.77.84199.19.77.1865.87.223.26157.22.126.128
hashes
urls
Sources & research credit
2 sourcesResearch by Microsoft Threat Intelligence · Microsoft
- Threat actors use agentic AI tooling to find and abuse exposed secrets www.microsoft.com
- VulnCheck: Microsoft Secret Hunter www.vulncheck.io
Microsoft Threat Intelligence blog (Nov 5, 2026) primary source; Todyl-observed related infrastructure noted; all IOCs (199.19.77.84, 199.19.77.18, 65.87.223.26, 157.22.126.128) verified from Microsoft post
Record & downloads
- Source record name
- Microsoft Threat Intelligence - ARTEX agents mining GitHub secrets into Entra & Azure Key Vault
- Entry ID
- microsoft-artex-github-secrets-keyvault-2026-11
- Catalog review
- November 6, 2026
- Category
- adversary-use-of-ai
- AI involvement confidence
- confirmed