mcp-server.io

agent-lint

com.runningunattended/agent-lint

30
security score

Checks CLAUDE.md, AGENTS.md or a system prompt for 12 safeguards unattended agents need.

GitHub stars
—
Last commit
never
Transport
streamable-http

Security scan

Last scanned 1 hour ago — static analysis of the published manifest.

  • lowManifest makes network requests.
  • criticalTool/description text references 'system prompt' — possible prompt injection.
  • mediumNo source repository linked — code cannot be audited.