EE
FR Contact

Cisco Talos says VOLTA-AUTODOXER malware uses Claude to rank victims' assets

In the wild Misuse Severity 3 significant Reported 55% Added by the register agent

Cisco Talos reports that a self-deleting Windows infostealer called VOLTA-AUTODOXER steals credentials, files and session data, then sends the collected evidence bundle to an AI model, by default Anthropic's Claude Opus 4.6, to rank the victim's valuables. The malware reportedly switches to other models if one refuses, and can skip the AI step entirely. The article describes the malware as a product that appears designed for resale.

What would have stopped it

An application-control policy that limits which processes may launch Chrome headless would block the malware's ABE decryption path, though not its AI stage or exfiltration.

Guardrails

0 of 8 failed
  1. G1 Least privilege Not assessed Did the agent hold only the access the task needed?
  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 Not assessed Could a responsible human see what it was doing and stop it in time?
  8. G8 Recovery Not assessed Could the damage be undone?

Sources

1 press
  1. New AI-driven Windows malware feeds stolen data to Claude to rank victims’ assets by value, then deletes itself — payload builds custom target assessment, can switch models if one refuses, or skip the AI step entirely Tom's Hardware, 1 Nov 2026
    “A self-deleting Windows infostealer that calls itself VOLTA-AUTODOXER steals everything it can from a victim’s PC, then asks an AI model, Anthropic’s Claude by default, to turn the haul into a target assessment, Cisco’s Talos research organization reports.”
    Press Quote checked Archived copy

Confidence 55% comes from these sources alone. How we score

History

  1. 2 Nov 2026Drafted by the register agent from Tom's Hardware (register agent)

Similar failures

All incidents
  1. EEAIR-2026-046 Oct 2026 Microsoft says China-linked Storm-0940 used ARTEX AI agents in ConnectWise attack ARTEX 73%
  2. EEAIR-2026-055 Oct 2026 Chainalysis says attackers used agentic techniques to breach internal systems Unidentified offensive agentic tools 92%
  3. EEAIR-2026-052 Oct 2026 TrendAI says CyberStrikeAI's 44 agents validated at least 19 Japanese targets CyberStrikeAI 64%