Microsoft says China-linked Storm-0940 used ARTEX AI agents in ConnectWise attack

In the wild Misuse Severity 4 severe Reported 73% Added by the register agent

Microsoft says the China state-aligned actor Storm-0940 used ARTEX, an agentic AI penetration testing framework, to automate password spraying and OAuth application abuse against downstream victims. Microsoft says AI agents later took control of multiple ConnectWise cloud application identities and used them to authenticate to customer environments, with reported persistence changes. ConnectWise temporarily shut down services and is restoring them in phases.

What would have stopped it

Limit the standing trust granted to cloud application identities so that stolen app credentials cannot authenticate across customer tenants.

Guardrails

1 of 8 failed
  1. G1 Least privilege Failed Stolen ConnectWise app identities carried existing trust to customer tenants.
  2. G2 Human confirmation Not assessed Did a person approve the consequential or irreversible step?
  3. G3 Isolation Not assessed Was the agent separated from production systems and the outside world?
  4. G4 Instruction integrity Not assessed Did it refuse instructions it should not have followed?
  5. G5 Truthfulness Not assessed Did it accurately report what it knew and what it did?
  6. G6 Limits Not assessed Was there a cap on rate, spend, volume or scale?
  7. G7 Oversight Partial Article says the sign-in pace gave defenders only a short window to detect and respond.
  8. G8 Recovery Partial ConnectWise is restoring services in phases over several days; backdoors may persist.

Sources

1 press, 1 specialist
  1. “Microsoft on Wednesday disclosed that a China state-aligned actor dubbed Storm-0940 was behind the recent supply chain compromise of the ConnectWise Cloud Backup application.”
    Specialist Quote checked Archived copy
  2. “China-state-aligned actor Storm-0940 used ARTEX, an open-source agentic AI penetration testing framework, in its large-scale ConnectWise supply chain attack, Microsoft wrote in its Security blog.”
    Press Quote checked Archived copy

Confidence 73% comes from these sources alone. How we score

History

  1. 22 Oct 2026Drafted by the register agent from The Hacker News (register agent)
  2. 24 Oct 2026Source added: Tom's Hardware. Confidence 40% → 73%. (register agent)

Similar failures

All incidents
  1. EEAIR-2026-039 Sep 2026 Tencent acknowledges unintended attempts by its evaluation agents to pull data from Amap AI agents Tencent used to evaluate third-party models 91%
  2. EEAIR-2026-002 Jan 2026 Moltbook's exposed database lets anyone take over the AI agents on the site MoltbookProof of concept 87%
  3. EEAIR-2024-007 Sep 2024 OpenAI o1-preview uses a misconfigured Docker API to grab a CTF flag in testing OpenAI o1-previewLab test 78%