skill-security-check vs io.github.Nekzus/npm-sentinel-mcp
skill-security-check is a plugin bundle for AI coding tools published by aliksir. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). io.github.Nekzus/npm-sentinel-mcp is an MCP server published by Nekzus. Marketplaces we read that list it: 3 (Official MCP Registry, Docker MCP Catalog, npm registry (MCP servers)). As of our marketplace pass on 2026-10-28. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  skill-security-check |  io.github.Nekzus/npm-sentinel-mcp |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 2.5.0 Forks (GitHub): 2 Stars (GitHub): 4 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 1.26.1 Downloads/month (npm): 1 487 Downloads/week (npm): 309 Forks (GitHub): 10 Stars (GitHub): 19 Not marked · First seen |
| Docker MCP Catalog | Not listed | Listed Version: sha256:d8e4bbc7dd5c Forks (GitHub): 10 Pulls (Docker Hub): 61 270 Stars (Docker Hub): 1 Stars (GitHub): 19 Not marked · First seen |
| npm registry (MCP servers) | Not listed | Listed Version: 1.26.1 Downloads/month (npm): 1 487 Downloads/week (npm): 309 Forks (GitHub): 10 Stars (GitHub): 19 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | skill-security-check | io.github.Nekzus/npm-sentinel-mcp |
|---|---|---|
| Marketplaces that list it (differs) | 1 (worse) | 3 (better) |
| Stars (GitHub) (differs) | 4 (worse) | 19 (better) |
| Pulls (Docker Hub) (differs) | No figure on Docker Hub | 61 270 |
| Forks (GitHub) (differs) | 2 (worse) | 10 (better) |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | Remote server or your machine |
| Transport (differs) | Not stated | stdio, Streamable HTTP |
| Tools it declares (differs) | Not published | 19 |
| Environment variables it asks for | Not published | Not published |
| Hooks it runs (differs) | 3 | Not published |
| Parts of the bundle (differs) | 4 | Not a bundle |
| Licence | MIT | MIT |
| Repository (differs) | github.com/aliksir/claude-code-skill-security-check | github.com/nekzus/npm-sentinel-mcp |
| Changes in the last 7 days | 0 | 0 |
| First seen (differs) | 2026-10-12 | 2026-10-11 |
| Endpoint at the last check (differs) | no remote endpoint we check | Responded 5 days ago, requires a key |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
skill-security-check
Security audit plugin that scans Claude Code skills, hooks, and MCP configurations for threats. Detects 37 attack patterns including prompt injection, data exfiltration, supply chain attacks (ToxicSkills/ClawHavoc), credential theft, reverse shells, backdoor persistence, API endpoint hijacking, Unicode homoglyph attacks, and context window poisoning. Includes runtime hooks for Bash command validation and MCP response inspection.
io.github.Nekzus/npm-sentinel-mcp
Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.
How to run each
skill-security-check As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install skill-security-check@claude-communityio.github.Nekzus/npm-sentinel-mcp As a local MCP server: npm package
claude mcp add --transport stdio npm-sentinel-mcp -- npx -y @nekzus/mcp-serverCommands built only from what the marketplaces declare; the full set for every client is on each card.
Only io.github.Nekzus/npm-sentinel-mcp has a remote endpoint we check. How we check endpoints
Tools each declares
The marketplaces of skill-security-check publish no list of tools, so we do not compare tools.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: skill-security-check · What it can do: io.github.Nekzus/npm-sentinel-mcp · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Package data comes from the public npm registry (registry.npmjs.org). Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.