v2026.09

Summary

ATLAS release v2026.09 contains 1 matrix, 16 tactics, 120 techniques, 88 sub-techniques, 40 mitigations, and 73 case studies. It adds new techniques such as Triggers in Multimodal Inputs, AI Agent Response Biasing, and Crafted AI Assistant Links, plus one new mitigation, AI Honeypots. It also updates existing techniques, mitigations, and case studies, including Generative AI Guardrails.

Related items

• InfoTop agent skill security resources — November 2026Similar attack · Adversa AI Blog
• InfoHow to Turn AI Red Team Findings Into Runtime ControlsSimilar attack · Straiker Blog
• MediumDocker Sandboxes vulnerability lets AI agents access sensitive files outside their sandbox (CVE-2026-103916) | Endor LabsSimilar attack · Endor Labs Blog
• MediumFree the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak BundlesSimilar attack · Check Point Research
• InfoRight Tool, Wrong Parameters: Defending LLM Agents Against Parameter PoisoningSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)