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
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add NVIDIA/SkillSpector -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add NVIDIA/SkillSpector -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add NVIDIA/SkillSpector -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add NVIDIA/SkillSpector -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/NVIDIA/SkillSpectorFrom the publisher
SKILL.md is not stored on this record yet. Open it on GitHub.
© 2026 Skills Rack.
---name: SkillSpectordescription: Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt…---# SKILL.mdOverview
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.
FAQ
Download SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/NVIDIA/SkillSpector.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.