A week of AI security research on system-prompt leaks, web-agent privacy risks, skill-hijack defenses, and a faster Anthropic disclosure clock.
LLMs Keep Secrets Poorly — and Agents Make It Worse
A week of AI security research on system-prompt leaks, web-agent privacy risks, skill-hijack defenses, and a faster Anthropic disclosure clock.
This field moves fast. gbrain was at v0.60.634.0 on the day I ran these tests — 10 November 2026 —...
A week of AI security research on system-prompt leaks, web-agent privacy risks, skill-hijack defenses, and a faster Anthropic disclosure clock.
"Learn AI engineering" usually means a dozen browser tabs and no order. I wanted one structured path,...