ResearchClawBench — security grade SAFE, quality 61/100

Security audit verdict: SAFE · quality 61/100

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 →

About ResearchClawBench

ResearchClawBench         Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery Quick Start Add Your Agent ResearchClawBench is a benchmark that measures

agentaiai-agentai-scientistai4scienceauto-researchbenchmarkclaudeclaude-codeclawdbot

Quick Facts

Stars264
Forks24
LanguageJupyter Notebook
CategoryCodex Skill
LicenseMIT
Quality Score61.21581102341/100
Open Issues2
Last Updated2026-09-17
Created2026-03-18
Platformsclaude-code, codex
Est. Tokens~24k

ResearchClawBench alternative? Top 6 similar tools

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.

  • AutoR by AutoX-AI-Labs · ⭐ 855

    AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk

  • AutoR by tangxiangru · ⭐ 806

    AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk

  • De-Anthropocentric-Research-Engine by Pthahnix · ⭐ 229

    De-Anthropocentric Research Engine — AI-powered academic research automation with deep literature survey, gap

  • Overture by SixHq · ⭐ 641

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • Anti-Autoresearch by wanshuiyin · ⭐ 152

    Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrica

  • open-skills by besoeasy · ⭐ 132

    Battle-tested skill library for AI agents. Save 98% of API costs with ready-to-use code for crypto, PDFs, sear

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Jupyter Notebook Agent Tools

Frequently Asked Questions

What is ResearchClawBench?

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.

What programming language is ResearchClawBench written in?

ResearchClawBench is primarily written in Jupyter Notebook. It covers topics such as agent, ai, ai-agent.

How do I install or use ResearchClawBench?

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.

What license does ResearchClawBench use?

ResearchClawBench is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to ResearchClawBench?

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.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools