v5.5.0
inforesearchIndustryLLM-Specific
securityresearch
Source: MITRE ATLAS ReleasesMarch 30, 2026
Summary
Version 5.5.0 adds new security techniques documenting threats to AI systems, including AI agent tool poisoning (when attackers corrupt tools that AI agents use), supply chain attacks, and cost harvesting (depleting computing resources through expensive queries). It also updates existing techniques and mitigations related to code signing and monitoring AI agent behavior.
Classification
Attack Type
Supply ChainModel PoisoningRAG PoisoningData Extraction
Affected Vendors
Anthropic
Related Issues
Monthly digest — independent AI security research
Original source: https://github.com/mitre-atlas/atlas-data/releases/tag/v5.5.0
First tracked: March 31, 2026 at 02:00 AM
Classified by LLM (prompt v3) · confidence: 85%