Orchesis AI Agent Security Scanner checks your AI agent configuration for security vulnerabilities. 80+ checks across 9 categories including CVE database matching, OWASP MCP Top 10 compliance, and IDE-specific config validation for Cursor, Claude Code, and OpenClaw. 100+ checks available via CLI. No signup required. All processing runs client-side — your config data never leaves your browser. Free, open source, MIT license.
orchesis verify — it finds and checks your config automatically.CVE database, malicious packages, typosquatting, version pinning
12 secret patterns, entropy detection, admin tokens, shared credentials
autoApprove, broad paths, sensitive file access, tool restrictions
Privileged mode, socket mounts, host network, sensitive paths
Unencrypted transport, TLS verification, remote endpoints, ports
Exfiltration paths, tool collisions, server count, shared credentials
Claude Code, Cursor, OpenClaw: sandbox, permissions, hooks, deny rules
Logging, context oversharing, prompt injection indicators
A2A authentication, shell interpreters, elevated execution