adversarial ml

SkillDRE: Dual-Stage Red-Team Evolution of Agent Skills via Pre-Execution and Runtime Feedbackarxiv.org

SkillDRE is an automated framework that evolves malicious AI agent skills using a dual-stage feedback loop, combining pre-execution scanning and runtime defense feedback. It achieved a 45.28% attack success rate against victim models, significantly outperforming baselines while bypassing scanners and maintaining benign functionality.