agent-guard
01Skill Claude CodeCodex
Scan AI agent skills, plugins, and MCP servers for malicious code BEFORE installation — catches prompt injection, credential theft, data exfiltration, and backdoors. Skills and the static MCP source scan use NVIDIA SkillSpector (static patterns + taint tracking + YARA + live OSV.dev CVE lookup; full LLM coverage…
2 1mo ago C 375 tokens
original MIT