Skip to content
  1. Home
  2. AI tools
  3. SkillSpector

SkillSpector

Security scanner that checks agent skills before you install them

What it is

A scanner from NVIDIA that inspects agent skills for vulnerabilities, malicious patterns, prompt injection and data-exfiltration risks, and produces a report you can use to gate installs. It runs as a CLI and can also be exposed as an MCP server. For anyone installing third-party skills into Claude Code, Codex or Gemini CLI.

Good for

  • Scan a skill repository before installing it
  • Gate skill installs in CI
  • Review a report on a suspicious skill

Install or run

uv tool install git+https://github.com/NVIDIA/skillspector.git

Command as given in the project README. Read the repository before you run anything on your machine.

What you need

Python with uv

Worth knowingA clean scan lowers risk but is not proof a skill is safe.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for security & quality

See the topic →
  • Security Guidance plugin

    NousResearch/hermes-agent

    Warns when written code contains known-dangerous patterns

    ToolGitHub stars: 263k
  • security-guidance

    anthropics/claude-plugins-official

    Security warnings on edits plus LLM diff review

    ToolGitHub stars: 47k
  • Langfuse

    langfuse/langfuse

    Open-source tracing, evals and cost tracking for LLM applications

    ToolGitHub stars: 37k
  • Promptfoo

    promptfoo/promptfoo

    CLI for evaluating and red-teaming prompts, agents and RAG apps

    ToolGitHub stars: 27k