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.
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.
Corelight found an MCP server pinned to one release that drifted through 15 dependency sets in five weeks, with the config untouched. 23 of 35 MCP servers it reviewed had a recommended install that resolves dependencies fresh from a public registry.
Darktrace Signal Labs showed that stolen Claude credentials let an attacker steer Claude Code agents through memory stores and pull a 1 GB file out through the Files API. No platform vulnerability is involved, and Darktrace has not seen it in the wild.