SkillSpector

NVIDIA/SkillSpector

★ 14,168 stars Python AI/LLM Updated today

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.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "skillspector": {
      "command": "uvx",
      "args": [
        "skillspector"
      ]
    }
  }
}

Or install with pip: pip install skillspector

README Excerpt

**Security scanner for AI agent skills.** Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. 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**.

Tools (20)

ANTHROPIC_API_KEYANTHROPIC_BASE_URLANTHROPIC_PROXY_API_KEYANTHROPIC_PROXY_API_VERSIONANTHROPIC_PROXY_ENDPOINT_URLAWS_PROFILEAWS_REGIONCAUTIONDO_NOT_INSTALLNVIDIA_INFERENCE_KEYOPENAI_API_KEYOPENAI_BASE_URLSAFESKILLSPECTOR_LOG_LEVELSKILLSPECTOR_MODELSKILLSPECTOR_MODEL_REGISTRYSKILLSPECTOR_PROVIDERSKILLSPECTOR_REASONING_EFFORTanthropicanthropic_proxy

Topics

agent-securityagent-skillsagentic-aiai-securityclaude-codemcpprompt-injectionsecurity-scannersecurity-toolssecurity-workflowsupply-chain-security

SkillSpector

Quick Install

README Excerpt

Tools (20)

Topics

Related AI/LLM Servers