threatdeck
Live 14:45 UTC ·

AI Stack Alert High For CISO, SOC / IR, AppSec, AI Eng AI-assisted

Threat actors use agentic AI tool ARTEX to harvest exposed secrets and abuse Entra ID service principals

Microsoft Threat Intelligence observed threat actors using the agentic AI offensive framework ARTEX to search public GitHub repositories for exposed credentials, application credentials, and AI inference API keys. In follow-on activity starting October 28, 2026, valid leaked application credentials were used for service principal sign-ins to Microsoft Entra ID tenants, and in one case an agent moved from GitHub secret search to Azure Key Vault exfiltration in five minutes.

Why it matters

Any organization with a secret committed to a public repository should treat it as compromised, since it stays usable until rotated. Attackers gain access to Key Vault contents, storage keys, AI service resources, and downstream tenants reachable through multitenant app credentials.

Do this

  1. Scan GitHub repositories you own for secrets, and enable GitHub public monitoring or secret scanning to find secondary exposures.
  2. Rotate any exposed credentials immediately. Remove client secrets, certificates, and federated credentials from affected apps, and rotate everything stored in Key Vaults those apps could read.
  3. Block 199.19.77.84/32 and review sign-in logs for 199.19.77.84 and 199.19.77.18, looking for failures followed by successes on service principals.
  4. Review Azure Key Vault, Storage, Entra audit, and Azure DevOps audit logs for secret reads, blob downloads, and changes to apps or pipelines.
  5. Review Azure RBAC permissions for service principals and move workloads toward managed identities where possible.

Signals

  • NoCISA KEV
  • 37/100Priority
  • 85%Confidence

Evidence

“agentic tooling like ARTEX allows threat actors to not only scan for secrets across multiple repositories at a quicker pace but also use the agents to analyze the output and conduct follow-on attacks”

Microsoft Security Blog

“Publicly exposed credentials remain usable until revoked or rotated; removing the original disclosure alone does not remediate the exposure.”

Microsoft Security Blog

“In one observed case, an AI agent progressed from searching for the client secrets in GitHub to exfiltrating data from Azure Key Vault in five minutes.”

Microsoft Security Blog

Sources

Affected / related

ARTEX, Microsoft, Microsoft Entra ID, Azure Key Vault, GitHub, Microsoft Defender for Cloud

Published 2026-11-05 23:46 UTC · updated 2026-11-10 00:24 UTC · AI-assisted summary, checked against quoted sources · How we score

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.