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

arXiv:2609.32400 · cs.CR, cs.AI · Submitted 2026-09-26 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/whfeLingYu/SkillDRE

Terminology

• Agent Skills — 16× in this paper · explained in 1 episode
• Accuracy — 7× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• Benchmarking — 5× in this paper · explained in 3 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Attack Success Rate (ASR) — 3× in this paper · explained in 2 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Iterative Refinement — 2× in this paper · explained in 3 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Procedural Knowledge — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Verifiability — 1× in this paper · explained in 2 episodes

Sources

• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement
• GLM-5: from Vibe Coding to Agentic Engineering
• SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries
• Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
• SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction
• Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
• AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
• Generative Skill Composition for LLM Agents
• A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs