OWASP Refreshes GenAI Security Guide, Adds 21 Risks and New Tools

OWASP GenAI Security Project Gets Update, New Tools Matrix outlines 21 identified risks and splits its tracking into generative AI and agentic AI to reflect rapid adoption and security concerns. The OWASP Foundation published a GenAI Data Security risks listing covering 21 potential data issues, including sensitive data leakage and unsanctioned data flows due to shadow AI.

Because the field is changing rapidly, the release comes only four months after the previous solutions guide, with providers expanding from 50 to more than 170, according to Scott Clinton, co-lead of the OWASP GenAI Security Project. The group plans to move to a six-month update schedule, saying the pace has slowed somewhat but remains brisk. The project aims to map evolving security needs for LLMs, GenAI, and agentic AI within a DevOps and SecOps cycle, connecting market solutions to OWASP’s documented risks.