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 NVIDIA · MCP Server · ★ 19.3k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is SkillSpector safe to install? View the security audit →
SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills (used by Claude Code, Codex CLI, Gemini CLI, etc.) execute with implicit trust and minimal vetting. Research shows that 26.1% of skills contain vulnerabilities and 5.2% show likely malicious intent. SkillSpector helps you answer: "Is this skill safe to install?" Documentation Development guide — Architecture, package layout, and how to extend the analyzer pipeline. Features Multi-format input: Scan Git repos, URLs, zip files, directories, or single files 64 vulnerability patterns across 16 categories: prompt injection, data exfiltration, privilege escalation, supply chain, excessive agency, output handling, system prompt leakage, memory poisoning, tool misuse, rogue agent, trigger abuse, dangerous code (AST), taint tracking, YARA signatures, MCP least privilege, and MCP tool poisoning Two-stage analysis: Fast static analysis + optional LLM semantic evaluation Live vulnerability lookups: SC4 queries OSV.dev for real-time CVE data with automatic offline fallback Multipl
| Stars | 19,308 |
| Forks | 1,687 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 75.7801042092503/100 |
| Open Issues | 158 |
| Last Updated | 2026-10-02 |
| Created | 2026-03-21 |
| Platforms | claude-code, cli, codex, mcp, python |
| Est. Tokens | ~18k |
These tools work well together with SkillSpector for enhanced workflows:
Looking for a SkillSpector alternative? If you're comparing SkillSpector with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
Installable GitHub library of 1,800+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravit
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable re
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c
Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with
Explore other popular mcp server tools:
SkillSpector is Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills befo. It is categorized as a MCP Server with 19.3k GitHub stars.
SkillSpector is primarily written in Python. It covers topics such as agent-security, agent-skills, agentic-ai.
You can find installation instructions and usage details in the SkillSpector GitHub repository at github.com/NVIDIA/SkillSpector. The project has 19.3k stars and 1687 forks, indicating an active community.
SkillSpector is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to SkillSpector on Agent Skills Hub include awesome-claude-skills, antigravity-awesome-skills, claude-skills. 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: