by NVIDIA · MCP Server · ★ 14.9k
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.
| Stars | 14,885 |
| Forks | 1,239 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 76.5327839230254/100 |
| Open Issues | 81 |
| Last Updated | 2026-08-22 |
| Created | 2026-03-21 |
| Platforms | claude-code, cli, codex, mcp, python |
| Est. Tokens | ~18k |
These tools work well together with SkillSpector for enhanced workflows:
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 14.9k 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 14.9k stars and 1239 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.