loading…
Search for a command to run...
loading…
Side-by-side comparison of two Model Context Protocol servers. Pick the right one for Claude Desktop, Claude Code, or Cursor.
Static security scanner for MCP server code, AI agent skills, and plugins. Detects 61 attack patterns across 4 severity levels — credential exfiltration, prompt
| Feature | Skill Audit | GitHub |
|---|---|---|
| Pricing | Free | Free |
| Installs | — | 42 108 |
| Rating | — | 4.9 (821) |
| Verified | — | |
| Hosted | — | Hosted |
| Tools | — | 5 |
| Category | development | development |
| Author | eltociear | GitHub |
| Repo | eltociear/skill-audit-mcp | modelcontextprotocol/servers |
Static security scanner for MCP server code, AI agent skills, and plugins. Detects 61 attack patterns across 4 severity levels — credential exfiltration, prompt injection, code execution, seed phrase harvesting, auth bypass, path traversal — with zero dependencies and 68+ real CVEs found in the wild.
Full GitHub access from Claude. Browse repos, read PRs, open issues, check CI runs, review diffs — without switching tabs.
Looking for something else? Browse all MCPs or check trending this week.