The authors systematically collected 83 reusable smart-contract audit skills, examining their structure, encoded security knowledge, workflows, and tool dependencies.
Reusable skills improve smart-contract audits, but model choice dominates
Across 83 audit skills and seven agent–model configurations, performance gains depended chiefly on the underlying model and whether the agent activated the skill.
Top University
Cuifeng Gao · Juantao Zhong · Jiachi Chen · Shuai Wang · Daoyuan Wu
Lingnan University · The Hong Kong Polytechnic University · State Key Laboratory of Blockchain and Data Security · Zhejiang University · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security
Research Digest··2 min read
Thread:Skill Selection for Agents
The authors collected smart-contract auditing skills used in the wild and evaluated them on EVMBench while analyzing how they changed agent execution.
Why this paper
From Zhejiang University and 5 others · Part of Skill Selection for Agents, now 14 papers
In one line
Smart contract audit skills improve vulnerability detection by up to 22.8% but effectiveness depends primarily on the underlying model.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
Concepts
agent skillssmart contract auditingvulnerability detectionskill triggeringaudit workflowmodel capability
§