After the Party: Growth, Governance, and Security Scanning in the OpenClaw Agent Skill Ecosystem

arXiv:2609.17274 · cs.SE, cs.AI, cs.CY · Submitted 2026-09-15 · Read on arXiv

cs.SE, cs.AI, cs.CY

Submitted: 2026-09-15

Updated: 2026-09-16

Comments: To appear in IEEE Digital Library as the 33rd Asia-Pacific Software Engineering Conference (APSEC 2026) conference proceedings. Accepted version, not camera ready version

Code: https://github.com/openclaw/openclaw

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

Terminology

• Accountability — 13× in this paper · explained in 2 episodes
• Agent Skills — 13× in this paper · explained in 1 episode
• Core — 10× in this paper · explained in 2 episodes
• Benchmarking — 4× in this paper · explained in 3 episodes
• Provenance — 4× in this paper · explained in 3 episodes
• AI Agents — 2× in this paper · explained in 2 episodes
• International Conference on Software Engineering — 2× in this paper
• Benchmark — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
• Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality
• Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats
• Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw
• A Security Analysis of the OpenClaw AI Agent Framework
• Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
• How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties