by agentscope-ai · Codex Skill · ★ 122
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 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 | 122 |
| Forks | 21 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 67/100 |
| Open Issues | 11 |
| Last Updated | 2026-08-03 |
| Created | 2026-05-15 |
| Platforms | python |
| Est. Tokens | ~16k |
🐾 PawBench English · 简体中文 A Model × Harness co-evaluation benchmark for agentic AI. 150 agent tasks · 9 models · 3 harnesses · task slices · diagnostic traces The same model can behave very differently once it is placed inside a real agent runtime.
These tools work well together with PawBench for enhanced workflows:
Looking for a PawBench alternative? If you're comparing PawBench with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
High-value AI skills repository for Codex, Claude Code, OpenClaw, agents, prompts, and automation workflows.
[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI
A curated collection of resources for 🌌 Azure OpenAI, 🦙 LLMs (+RAG, Agents). Monthly Updates.
autonomous systems engineering cli agent for any cloud environment: AWS, GCP, Cloudflare, etc
The Runtime Security Layer for OpenClaw/Hermes-agent, the essential safety harness for PII & sensitive credent
An agent runtime for Python. Give your agent real work. Keep control: every action checked before it runs, eve
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 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: