AgentHazard (OpenClaw) - System RCE: leaderboard
Metric: Attack success rate (%) on the system remote code execution (RCE) instances (arbitrary system command execution on the host or container), with the model running inside the OpenClaw open-source agent framework (browser, shell and file-system tools; one isolated Docker container per task), over AgentHazard instances (harmful objectives embedded in locally legitimate multi-step workflows, ten risk categories and ten attack strategies; the evaluated runs cover 1,000 instances), judged on the full trajectory (round_all) by Gemini-3-Flash, which labels a trajectory harmful when it realizes the objective; backbones served through an OpenAI-compatible API; lower is better. Source: arxiv.org. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 29 |
| 2 | Qwen 2.5 Coder 32B Instruct | 40.4 |
| 3 | Kimi K2.5 | 44 |
| 4 | Qwen 3 VL 235B A22B Instruct | 60 |
| 5 | Qwen 3 32B | 65 |
| 6 | Kimi K2 | 68 |
| 7 | GLM-4.6 | 69 |
Interactive version: theaggregate.ai/benchmark?slug=agenthazard-openclaw-system-rce · How It Works · Data refreshed daily, snapshot 2026-10-07.