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.

语言：Python · GitHub 星标：23,871 · Fork：2,061

话题：agent-security · agent-skills · agentic-ai · ai-security · claude-code · mcp · prompt-injection · security-scanner

在 GitHub 上查看原仓库