# Demystifying Agent Skills for Smart Contract Auditing: Design, Effectiveness, Behavioral Impact

arXiv: https://arxiv.org/abs/2609.29454 · HTML: https://mlsanity.com/paper/2609.29454/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 51 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 18 of 18)

- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [SkillOpt: Executive Strategy for Self-Evolving Agent Skills](https://mlsanity.com/paper/2605.23904/) (2026)
- [Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale](https://mlsanity.com/paper/2601.10338/) (2026)
- [SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?](https://mlsanity.com/paper/2603.15401/) (2026)
- [GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis](https://mlsanity.com/paper/2308.03314/) (2023)
- [SkillNet: Create, Evaluate, and Connect AI Skills](https://mlsanity.com/paper/2603.04448/) (2026)
- [You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects](https://mlsanity.com/paper/2412.10133/) (2024)
- [Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications](https://mlsanity.com/paper/2403.16073/) (2024)
- [PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation](https://mlsanity.com/paper/2405.02580/) (2024)
- [SkillReducer: Optimizing LLM Agent Skills for Token Efficiency](https://mlsanity.com/paper/2603.29919/) (2026)
- [EVMbench: Evaluating AI Agents on Smart Contract Security](https://mlsanity.com/paper/2603.04915/) (2026)
- [SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System](https://mlsanity.com/paper/2605.09341/) (2026)
- [Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose](https://mlsanity.com/paper/2606.18051/) (2026)
- [Re-Evaluating EVMBench: Are AI Agents Ready for Smart Contract Security?](https://mlsanity.com/paper/2603.10795/) (2026)
- [Skill Availability and Presentation Granularity in Large-Language-Model Agents: A Controlled SkillsBench Study](https://mlsanity.com/paper/2605.31408/) (2026)
- [LinkAnchor: An Autonomous LLM-Based Agent for Issue-to-Commit Link Recovery](https://mlsanity.com/paper/2508.12232/) (2025)
- [OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models](https://mlsanity.com/paper/2606.16774/) (2026)
- [Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining](https://mlsanity.com/paper/2606.20363/) (2026)

## Abstract (arXiv)

LLM agents, notably Claude Code and OpenAI Codex, are emerging as versatile tools beyond coding agents only. These agents can be enhanced with skills---reusable artifacts that package domain knowledge, workflows, and tool-use instructions. To date, however, little is known about how such skills are designed or how they affect agent effectiveness and behavior in practice. In this paper, we investigate these questions in smart contract security auditing, a domain in which agents have shown substantial promise. We systematically collect 83 smart contract audit skills from the wild and evaluate them on EVMBench across seven agent--model configurations. Our study examines three dimensions: (i) the design characteristics of audit skills, including their structure, knowledge representations, workflows, and tool dependencies; (ii) their effectiveness in improving vulnerability detection; and (iii) their influence on agent execution trajectories. We find that audit skills are mostly lightweight but heterogeneous in design, covering a broad yet imbalanced range of vulnerability types. Their effectiveness is determined primarily by the model rather than the agent harness: Codex/GPT-5.5 achieves the largest gains, improving detection score by 22.8% and captured award by 43.2%. We further find that skill triggering is a key bottleneck. When triggered, skills preserve a shared six-stage audit workflow while exhibiting distinct loading patterns and differential effects on agent behavior across configurations. We release our skill corpus and artifacts to support future research.