cnki-skills — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

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 cookjohn · MCP Server · ★ 849

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is cnki-skills safe to install? View the security audit →

About cnki-skills

CNKI Skills for Claude Code English | 中文 English Claude Code skills that let Claude interact with CNKI (中国知网) through Chrome DevTools MCP. Search papers, browse journals, check indexing status, download PDFs, and export to Zotero — all from the Claude Code CLI. Prerequisites Claude Code CLI installed Chrome browser (login handled manually for downloads) Zotero desktop app (optional, for export) Python 3 (optional, for Zotero push script) Skills Extract full paper metadata (

Quick Facts

Stars849
Forks75
LanguagePython
CategoryMCP Server
Quality Score66.6190990497022/100
Open Issues7
Last Updated2026-03-13
Created2026-02-28
Platformsbrowser, claude-code, mcp, python
Est. Tokens~29k

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is cnki-skills?

cnki-skills is CNKI (中国知网) skills for Claude Code — search, browse journals, download PDFs, export to Zotero via Chrome DevTools MCP. It is categorized as a MCP Server with 849 GitHub stars.

What programming language is cnki-skills written in?

cnki-skills is primarily written in Python.

How do I install or use cnki-skills?

You can find installation instructions and usage details in the cnki-skills GitHub repository at github.com/cookjohn/cnki-skills. The project has 849 stars and 75 forks, indicating an active community.

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 MCP Server tools