Discover great AI tools
📢 NoticeWebsite launched:DeepToSeek AI tools directory is live. Submit great tools and get featured!
Home / Open Source Radar / Other / SkillSpector

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 before you install them.

Stars26.7k
Forks2.4k
LanguagePython
LicenseApache-2.0
Last push2026-11-18

About this project

SkillSpector is an open-source AI project on GitHub: 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 before you install them. It is a general-purpose AI project that does not fit neatly into a single category, so the README is the fastest way to judge whether it matches your use case. It is maintained by NVIDIA and published as a public repository you can read, fork and run yourself.

On GitHub the repository is tagged agent-security, agent-skills, agentic-ai, ai-security, claude-code, mcp, prompt-injection, security-scanner, security-tools and security-workflow, which is a fair summary of what it covers. Scope varies a lot across this group: some are small utilities, others are full platforms, and the amount of setup differs accordingly.

It is written mainly in Python and released under APACHE-2.0, a permissive license — commercial use is fine as long as copyright notices are kept. It is actively maintained: the most recent commit landed on November 18, 2026.

To try it, clone the repository and follow its README; that file is the canonical install guide. There is also a project page at https://docs.nvidia.com/skills/scanning-agent-skills for documentation or a hosted demo. Because it runs on your own infrastructure, budget time for environment setup: dependencies, model weights and configuration usually take longer than the first successful run.

Key facts as recorded on GitHub: 26,689 stars; 2,378 forks; primary language Python; license APACHE-2.0; last commit on November 18, 2026; topics agent-security, agent-skills, agentic-ai, ai-security, claude-code, mcp.