Arctic Wolf says attackers used AntiFox AI agents in AWS credential theft
Arctic Wolf reportedly observed attackers using self-managed AntiFox agentic penetration-testing instances hosted on Alibaba Cloud. The attackers used valid AWS identities to make hundreds of API requests in about 30 minutes, and in some cases obtained production secrets. Amazon says AWS services were not compromised and that the threat actors used credentials taken from customers' compromised applications.
Disputed. Amazon says AWS services were not compromised and operated as designed, and that the threat actors used credentials taken from customers' compromised applications.
What would have stopped it
Keeping long-term AWS access keys out of application configuration files, as Amazon recommends, would limit what stolen credentials can reach.
Guardrails
- G1 Least privilege Not assessed Did the agent hold only the access the task needed?
- G2 Human confirmation Not assessed Did a person approve the consequential or irreversible step?
- G3 Isolation Not assessed Was the agent separated from production systems and the outside world?
- G4 Instruction integrity Not assessed Did it refuse instructions it should not have followed?
- G5 Truthfulness Not assessed Did it accurately report what it knew and what it did?
- G6 Limits Not assessed Was there a cap on rate, spend, volume or scale?
- G7 Oversight Not assessed Could a responsible human see what it was doing and stop it in time?
- G8 Recovery Not assessed Could the damage be undone?
Sources
-
“In one intrusion, the AntiFox-linked source cycled through multiple AWS identities and generated hundreds of cross-service API requests within approximately half an hour.”
-
“Although most of these attempts were blocked, the attacker was successful in some cases and obtained production secrets.”
-
“Cybercriminals are using an open source AI-powered pentesting platform called AntiFox to steal login credentials and access people’s Amazon Web Services (AWS) environments.”
Confidence 87% comes from these sources alone. How we score
History
- 12 Nov 2026Drafted by the register agent from BleepingComputer (register agent)
- 13 Nov 2026Source added: TechRadar. Confidence 55% → 80%. (register agent)
- 13 Nov 2026Source added: Arctic Wolf Labs. Confidence 80% → 87%. (register agent)