Amazon Threat Intelligence says decoy LLM APIs captured ARTEX agents' working memory between Oct. 3 and Nov. 5, 2026, exposing campaigns the agents reported as stealing AI model keys and trying to beat crypto exchange KYC with deepfakes.
The latest AI security developments, threats, and industry updates.
Amazon Threat Intelligence says decoy LLM APIs captured ARTEX agents' working memory between Oct. 3 and Nov. 5, 2026, exposing campaigns the agents reported as stealing AI model keys and trying to beat crypto exchange KYC with deepfakes.
Cursor's Nov. 13 update says an access key it issued to Fireworks AI was exposed and used to copy agent traces, and that a stolen credential from that data was used to plant the fake Claude Code extension.
Cloudflare's Cloudforce One says over 50 AI penetration-testing framework families scanned its customers in three days, and that ARTEX and its forks are over 60% of the orchestrators it tracks. It also describes a token-driven intrusion.
The FBI and DOJ seized FaceStealer infrastructure on November 12. North Korean actors replay recorded webcam footage of past victims in fake Zoom and Teams calls, now add deepfakes, and have gone after open-source maintainers.
Depi's Research Team reported a chain against openai/codex that began with a prompt injection in a GitHub issue and ended in a persistent backdoored workflow. Bugcrowd lists it as accepted and fixed, with a Bugcrowd priority of P1.