Skip to content
Neural Daily

ResearchNews

ARTEX: AI agents go from GitHub secrets to Key Vault

🇭🇺 Olvasd el magyarul →

Microsoft Threat Intelligence says attackers are using ARTEX, an agentic AI framework, to find leaked keys in public GitHub repositories and sign in to Entra ID tenants with them. In one case it took five minutes to go from a GitHub search to Azure Key Vault exfiltration.

· 4 min read

A Microsoft Security Blog borítóképe az agentic AI támadásokról szóló elemzéshez
Image: Microsoft · Press kit · Source

Updated: November 14, 2026, 20:28 (Europe/Budapest): Amazon and Check Point have also reported ARTEX campaigns. Details are in the new section below.

What Microsoft saw

In an analysis published November 5, Microsoft Threat Intelligence says attackers have been using agentic AI tooling since August 2026 to send large volumes of secret searches to GitHub. Queries typically combine a target organization's name, secret-related keywords and cloud or AI provider keywords. Microsoft cites ARTEX, an open-source offensive framework, as an example.

An old technique got a new pace. Hunting for leaked keys used to be slow because a human had to review the repos. An agent analyzes the hits itself and moves straight to the next step. In one case Microsoft measured five minutes from a client secret found on GitHub to data leaving Azure Key Vault.

What the agent did once inside

From October 28, Microsoft saw successful service principal sign-ins at several customers from 199.19.77.84, using leaked but still valid application credentials. In some cases a vendor's multitenant app credential was compromised at the source, opening a path into several downstream tenants.

Once signed in, the agent went after operations that return more credentials: storage account keys, App Service settings, connection strings and AKS user credentials. It read Key Vault secrets, downloaded SharePoint and OneDrive files, searched through Graph and looked for secrets in Azure DevOps. It also used Run Command to execute scripts on Azure VMs.

One detail stands out: adaptive troubleshooting. When an ARM call returned HTTP 400 because of a wrong API version, the agent retried 28 to 80 seconds later with a corrected version and got a 200. That is machine speed, not a human at a keyboard. The agent also focused on API keys for AI providers, which Microsoft says it may have used to run more of its own workload on stolen AI resources.

VulnCheck's canaries caught the same IP through a different door, exploiting Langflow to pull credentials straight off the server (VulnCheck).

What to do now

  • Treat anything that ever reached a public repo as compromised. Deleting the commit is not enough; rotate the key.
  • Turn on GitHub secret scanning and push protection, and extend public monitoring to repos outside your organization.
  • Use managed identities instead of client secrets wherever possible.
  • In Entra sign-in logs, errors AADSTS7000215 and AADSTS7000222 mean someone holds an old credential for your app. A failure followed by a success is urgent.
  • Alert on behavior too: one IP trying three or more service principals with mixed success.

Microsoft says decoys, tarpits and fake wins work well against autonomous attackers, because the agent believes it is done and stops. The full post includes KQL hunting queries and indicators (Microsoft Security Blog).

Update: Amazon's decoys captured the agents' memory

Amazon Threat Intelligence says that from October 3 to November 5 its MadPot decoy sensors, posing as popular LLM inference APIs, captured requests from ARTEX agents (AWS). Because agents send their full context to the LLM, the requests carried the campaigns' operating memory: system prompts, tool histories and targets.

  • The largest campaign stole API keys for AI models and cloud credentials, with stolen keys paying for the inference behind further key hunting.
  • Operators told the agents to treat credentials public for more than 30 days as low-value; fresh leaks were the priority.
  • Another campaign tried to bypass crypto-exchange KYC checks with real-time deepfake video.
  • Check Point found more than 1,800 publicly exposed ARTEX instances. Most operators used Chinese models, with the DeepSeek Flash family most common.

The practical advice has not changed, it has just become more urgent: rotate any leaked AI API key immediately, because agents are hunting for exactly the fresh leaks.

Why it matters

This is the mirror image of the defensive side. We covered how OpenAI's AI pipeline found 948 Linux root exploits (OpenAI's AI pipeline found 948 Linux root exploits). Now the same acceleration shows up on the attacker's side. If a key gets you to Key Vault in five minutes, a weekly secret scan is too slow: you need push protection and short-lived credentials.

Related articles