Microsoft: Threat actors use agentic ARTEX framework to steal cloud secrets in 5 minutes
cyb3rops · x · 2026-11-16
Microsoft Threat Intelligence reports that attackers are abusing the agentic AI framework ARTEX to scan public GitHub repos for exposed secrets, then weaponizing them against Entra ID and Azure. In one case, an AI agent went from discovering a client secret on GitHub to pulling data out of Azure Key Vault in five minutes — a landmark case of agentic tooling turned offensive.
More from Safety
- Human oversight is broken: monitoring systems are themselves misaligned in correlated ways — davidmanheim · 2026-11-16
- Cisco Talos warns AI-powered pentesting frameworks like ARTEX are automating full attack chains in the wild — cyb3rops · 2026-11-16
- Stop installing skills and MCP servers from viral threads unread — weswinder · 2026-11-16
- Lightcone evaluator Nathan Young publishes $5m–$12m funding rationale, gets one comment — NathanpmYoung · 2026-11-16
- Local Qwen Model Appears to Disconnect a USB Controller via Web Search Tool — BrightCandle · 2026-11-15
- X3Guard-150M: An Edge-Ready Prompt Guard Flagging Harmful and Adversarial Prompts — DingyAtoll · 2026-11-15