No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by InternScience · Codex Skill · ★ 264
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ResearchClawBench safe to install? View the security audit →
ResearchClawBench         Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery Quick Start Add Your Agent ResearchClawBench is a benchmark that measures
| Stars | 264 |
| Forks | 24 |
| Language | Jupyter Notebook |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 61.21581102341/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-17 |
| Created | 2026-03-18 |
| Platforms | claude-code, codex |
| Est. Tokens | ~24k |
Looking for a ResearchClawBench alternative? If you're comparing ResearchClawBench 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.
AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk
AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk
De-Anthropocentric Research Engine — AI-powered academic research automation with deep literature survey, gap
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrica
Battle-tested skill library for AI agents. Save 98% of API costs with ready-to-use code for crypto, PDFs, sear
Explore other popular codex skill tools:
ResearchClawBench is 🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery. It is categorized as a Codex Skill with 264 GitHub stars.
ResearchClawBench is primarily written in Jupyter Notebook. It covers topics such as agent, ai, ai-agent.
You can find installation instructions and usage details in the ResearchClawBench GitHub repository at github.com/InternScience/ResearchClawBench. The project has 264 stars and 24 forks, indicating an active community.
ResearchClawBench is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to ResearchClawBench on Agent Skills Hub include AutoR, AutoR, De-Anthropocentric-Research-Engine. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: