github.comrepoMITRE ATLAS v2026.08 release — autonomous agent techniques
Release notes for MITRE ATLAS v2026.08, the adversarial AI/ML knowledge base (now 1 matrix, 16 tactics, 114 techniques, 83 sub-techniques, 39 mitigations, 72 case studies). This version renames the "AI Attack Staging" tactic to "AI Attack Adaptation," generalizes several techniques (e.g., Cloud Service Discovery → Enterprise Resource Discovery, Process Discovery → Enterprise Environment Discovery, Reverse Shell → Cyber Communication Channel), and updates mitigations and techniques like LLM Prompt Crafting and Retrieval Content Crafting.
TL;DR MITRE ATLAS v2026.08 adds/renames tactics and techniques covering AI attack adaptation, agent recon, and LLM prompt/retrieval crafting.
Organisations named here
- AI Attack Staging
Technologies named here
- MITRE ATLAS
Techniques named here
- AI Attack Adaptation
- Enterprise Resource Discovery
- Enterprise Environment Discovery
- Cyber Communication Channel
- Develop Capabilities
- LLM Prompt Crafting
- Retrieval Content Crafting
- Cloud Service Discovery
- Process Discovery
- Reverse shell
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle