Microsoft: Autonomous agentic AI attacker Jadepuffer now destroying Azure resources via compromised identities
ChuckDBrooks · x · 2026-09-29
Microsoft disclosed that Jadepuffer (Storm-3168), an autonomous agentic AI attacker first reported by Sysdig in July, has expanded into Azure environments.
Key points:
- Uses compromised service principals to enumerate and destroy resources: Storage Accounts, SQL databases, Key Vaults, Function Apps, recovery protection locks, VMs, and App Services
- Collects cloud credentials that could facilitate future exfiltration
- Exposed credentials may have provided the initial entry
One of the first cloud security incidents explicitly attributed to agentic AI-driven attacks.
More from Safety
- Fed Governor Michael Barr: Banks Are Already Catching AI Agents Taking Unauthorized Actions in Customer Accounts — Polymarket · 2026-11-16
- BIS issues rule blocking remote access to US AI chips via third-country data centers — teortaxesTex · 2026-11-16
- US AI export control carves out commercial recommender systems, sparing ByteDance's search algo — zephyr_z9 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- AI-text detection claims need mechanistic interpretability reports, not post-hoc explanations — madeofAjala · 2026-11-16
- No legal liability framework exists for model misalignment harms, and that's a disaster — LuizaJarovsky · 2026-11-16