by AI45Lab · Agent Tool · ★ 277
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 277 |
| Forks | 32 |
| Language | Python |
| Category | Agent Tool |
| License | AGPL-3.0 |
| Quality Score | 68/100 |
| Last Updated | 2026-11-19 |
| Created | 2026-04-01 |
| Platforms | docker, python |
| Est. Tokens | ~15k |
OpenART OpenART is an executable benchmark for evaluating the safety of tool-using code agents in long-running, evolving environments. This repository contains its Docker-based runtime, three runnable high-complexity tasks, and the managed tools required by those tasks. OpenART is the agent version of OpenRT. [09/02/2026] ⭐ OpenART reached the 100-star milestone on GitHub.
These tools work well together with OpenART for enhanced workflows:
Looking for a OpenART alternative? If you're comparing OpenART with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha
Open-source adversary emulation for AI agents and MCP servers.
Deterministic safety solutions for probabilistic AI agents
🛡️ A curated list of resources on agent skills security: attacks, defenses, frameworks, and benchmarks for se
Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: