Company news
MITRE ATLAS September Release Adds 11 AI Agent Attack Techniques in Collaboration with Zenity Labs
Published 17 September 2026
WHAT HAPPENED
MITRE ATLAS released its September update adding 11 new techniques and subtechniques for AI agent attacks, developed in collaboration with Zenity Labs. The release documents attack methods across agent reconnaissance, manipulation, abuse, and defenses, plus includes a case study on AI recommendation poisoning.
WHO IS INVOLVED
MITRE ATLAS partnered with Zenity Labs to research and document the new attack techniques. The framework serves defenders working with AI agents that connect to enterprise data and tools.
WHY IT MATTERS
As AI agents become more integrated into enterprise environments, understanding the full attack chain from reconnaissance through exploitation is critical for defenders. The new techniques provide a shared reference for identifying and defending against real-world threats to AI agent systems.
- Type
- Partnership
- Category
- AI Security
- Source
- linkedin.com ↗
See Zenity’s full company record.
Look up its funding history, investors, hiring and competitors in Mandos. Choose a platform plan, or request access to one company for free.
- Funding history and investors
- Hiring trends and departments
- Competitor comparisons
- Scores and supporting data