SkillAtlas: An Attack Trace Library for Agent Skills

arXiv:2609.13353 · cs.CR, cs.AI · Submitted 2026-09-11 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-09-11

Updated: 2026-09-28

Comments: Accepted at REALM @ EMNLP 2026 (non-archival workshop paper). 9 pages, 4 figures

Project page: https://skillatlas.top

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Trace — 13× in this paper · explained in 2 episodes
• Agent Skills — 12× in this paper · explained in 1 episode
• Accuracy — 7× in this paper · explained in 1 episode
• Benchmark — 6× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 4 episodes
• Clustering — 2× in this paper · explained in 2 episodes
• Commentary — 2× in this paper · explained in 2 episodes
• GRPO — 2× in this paper · explained in 6 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• BInstruct with Group Relative Policy Optimization — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 4 episodes

Sources

• SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement
• SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
• Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
• Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections
• Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Universal and Transferable Adversarial Attacks on Aligned Language Models

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