SkillSpector

NVIDIA/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.

Install

GitHub
NVIDIA/SkillSpector
Website
docs.nvidia.com
Stars
★ 21.4k
License
Apache-2.0
Language
Python
Last push
Oct 23, 2026
Topics
agent-security · agentic-ai · ai-security · mcp · prompt-injection · security-scanner

Good for

Getting started

  1. Install with npx skills add NVIDIA/SkillSpector
  2. For the CLI, run uv tool install git+https://github.com/NVIDIA/skillspector.git
  3. Or use Docker: docker run --rm -v "$PWD:/scan" skillspector scan ./my-skill/ --no-llm
  4. Read the 0-100 risk score and severity labels before deciding to install

Before you install

The CLI needs Python unless you run it through Docker. Optional LLM semantic analysis needs credentials in a .env file, and the default configuration targets DeepSeek.

Summarized by AI from the project docs; check the official docs before relying on it.

Similar tools

More in Community skills →

Source GitHub · All rights belong to the original creators