June 4, 2026
Open-source methodology by OWASP, CoSAI, CSA, and NIST contributors enables enterprises to compare AI agents by security risk for the first time
Read moreJune 4, 2026
Open-source methodology by OWASP, CoSAI, CSA, and NIST contributors enables enterprises to compare AI agents by security risk for the first time
Read moreJune 4, 2026
Open-source methodology by OWASP, CoSAI, CSA, and NIST contributors enables enterprises to compare AI agents by security risk for the first time
Read more
Reports, whitepapers, and reference material on securing GenAI and agentic AI systems.
June 4, 2026
Open-source methodology by OWASP, CoSAI, CSA, and NIST contributors — 100+ AI agents scored and compared by security risk.
May 21, 2026
We ran involuntary in-context learning (IICL) attacks against 100 model configurations from 17 vendors — 24,956 adversarial probes. The full ranking.
March 9, 2026
The full technical reference behind our ASI05 guide — five attack vectors in depth, a five-layer defense architecture, and an architect's checklist.
February 15, 2026
The first comprehensive open-source security solution for OpenClaw agents — 50 audit checks and automated hardening, aligned with OWASP and MITRE.
September 17, 2025
The most comprehensive analysis of Model Context Protocol vulnerabilities to date — 25 ranked MCP security flaws, a shared taxonomy, and how to mitigate them.
July 30, 2025
Real breaches. Real consequences. Lessons the industry can't afford to ignore.
