AI Security

Advisories, threat intelligence, and research. RSS feed

Recent Advisories

LangChain Core serialization injection allows arbitrary code execution

GitHub Copilot prompt injection via PR descriptions enables RCE

View all advisories

Threat Frameworks

MITRE ATLAS Adversarial ML threat matrix — 16 tactics, 84 techniques, 42 case studies ATLAS Navigator Interactive coverage mapping and threat modeling tool atlas-data Machine-readable YAML — all tactics, techniques, mitigations OWASP LLM Top 10 Top 10 security risks for LLM applications NIST AI RMF AI risk management framework CISA AI Security Federal cybersecurity guidance for AI systems SAFE-AI Report MITRE technical report on securing AI systems (PDF)

Analysis & Research

security Apr 11

MITRE ATLAS: the adversarial threat matrix for AI systems

A comprehensive guide to MITRE ATLAS — 16 tactics, 84 techniques, and 42 case studies for understanding adversarial threats to AI/ML systems.

security Apr 10

Prompt injection in 2026: taxonomy, real-world exploits, and defenses

A technical breakdown of prompt injection attack classes, real CVEs, and the defense mechanisms that work — and those that don't.

security Apr 7

OWASP LLM Top 10 in practice — what each risk looks like in production

Concrete attack scenarios for each OWASP LLM risk, mapped to real CVEs and agentic AI systems. Not a summary — a practitioner's guide.