Microsoft observes Threat actors using agentic AI to find exposed secrets
Microsoft Threat Intelligence observed threat actors using an agentic AI offensive framework called ARTEX to scan public GitHub repositories for exposed credentials, application keys and AI inference‑related API keys. In one instance the AI agent moved from scanning GitHub to exfiltrating data from an Azure Key Vault in just five minutes. The attacks began on October 28, 2026, with sign‑ins from…
Key points
- Microsoft observed threat actors using ARTEX to scan GitHub for secrets
- An AI agent exfiltrated data from Azure Key Vault in five minutes
- Threat actors used compromised application credentials to sign into Entra ID from IP 199.19.77.84
Microsoft warns that exposed secrets in public code remain usable until revoked or rotated, and recommends scanning repositories, removing secrets, rotating keys, and using managed identities. The company also advises blocking the offending IPs, revoking sessions, and enabling Azure Defender and Sentinel Deception to detect and slow autonomous AI attacks.
Threat actors use agentic AI tooling to find and abuse exposed secrets
microsoft.com · 5 November 2026
Loading the full article…
This text was published by microsoft.com and written by Microsoft Threat Intelligence, Microsoft Security Research. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Enterprise & Industry
All →- OpenAI says GPT-6 Astra designed a hardware device from scratch in under a week · 13 src
- Former BI engineer rewrites 25 incident response manuals with Notion AI and Claude in six weeks · 1 src
- OpenAI partners with Australian universities to deploy ChatGPT Edu · 1 src
- Square Peg backs Future Secure AI to build enterprise AI co-workers · 1 src
- Airbnb plans to launch an AI travel agent in the first half of 2027 · 3 src
Comments
via GitHub Discussions