NVIDIA

SkillSpector

#111 this weekPython

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.

Stars
24k
Last 7 days
+2,283
Last 30 days
+4,837
Forks
2.1k
Created Mar 21, 2026License Apache-2.02,283 stars in the last 7 days
  • agent-security
  • agent-skills
  • agentic-ai
  • ai-security
  • claude-code
  • mcp
  • prompt-injection
  • security-scanner
  • security-tools
  • security-workflow
  • supply-chain-security

Weekly star counts from the GitHub API, refreshed once a day. GitHub doesn’t keep unstars, so past weeks only count stars that are still there.

Faundr

Build it with AI, without losing control.

Faundr keeps your project’s memory, blocks what can’t be undone and tells you if it’s safe to launch, inside Claude Code and Codex.