N/A

eltociear/Skill Audit MCP

mcp agent Offline

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.

Scan Scheduled

This agent is queued for security scanning. It will be graded in the next scan batch.

What We Know

Browse more: Search all agents Ecosystem Report