v2026.09
Summary
ATLAS v2026.09 is an updated database of AI security threats that now includes 120 techniques and 40 mitigations for defending AI systems. The update adds new attack methods like prompt injection (tricking an AI by hiding malicious instructions in its input), AI agent compromises, and exposed AI infrastructure scanning, along with new defensive strategies including AI honeypots (fake AI systems designed to catch attackers).
Classification
Affected Vendors
Related Issues
CVE-2026-63086: text-generation-inference through 3.3.7 contains a server-side request forgery (SSRF) vulnerability in the OpenAI-compat
CVE-2026-34371: LibreChat is a ChatGPT clone with additional features. Prior to 0.8.4, LibreChat trusts the name field returned by the e
Original source: https://github.com/mitre-atlas/atlas-data/releases/tag/v2026.09
First tracked: September 15, 2026 at 02:01 PM
Classified by LLM (prompt v3) · confidence: 85%