Microsoft

When prompts become shells: RCE vulnerabilities in AI agent frameworks

New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these ...

Mozilla says 271 vulnerabilities found by Mythos have “almost no false positives”

Unlike previous vulnerability disclosure slop, Grinstead said, the details provided by its harness-guided Mythos analysis, ...
IEEE

Toward Explainable AI in Spacecraft Health Monitoring: Comparative Benchmarking of Anomaly Detection Models and Open-Source Datasets

Abstract: The growing autonomy and complexity of spacecraft systems demand intelligent, interpretable, and resilient onboard health monitoring. This paper presents a dual benchmarking study of anomaly ...

One command turns any open-source repo into an AI agent backdoor. OpenClaw proved no supply-chain scanner has a detection category for it

CLI-Anything generates SKILL.md files that AI agents trust and execute. Snyk found 13.4% of agent skills contain critical ...
IEEE

FPDetection: False Positives Detection in Static Code Analysis with Deep Learning and LLM

Abstract: Security defects pose substantial risks to system integrity. SAP HANA Cloud, a secure database platform, undergoes regular static code analysis to enhance its robustness. However, a ...