Security

Security

Prompt Injection Shield

Detects and blocks injection attempts:

• Pattern matching for known techniques (ignore instructions, DAN, base64)
• Keyword density analysis (strict mode)

{ "security": { "shield": { "enabled": true, "mode": "standard" } } }

Sandbox Modes

Mode	Description
host	Direct execution (default)
docker	Docker container isolation
none	No sandboxing

Autonomy Modes

Mode	Description
supervised	Approval required for dangerous tools (default)
autonomous	All tools auto-approved
locked	No tool execution

Tool Access Control

{
  "security": {
    "allowedTools": ["shell", "read_file", "web_search"],
    "deniedTools": [],
    "networkAllowlist": ["api.github.com"]
  }
}

Gateway Hardening

• Rate limiting (30 req/min API, 5 req/min login)
• CORS (localhost only)
• Security headers (XSS, frame, content-type)
• 24h token TTL
• Timing-safe password comparison
• AES-256-GCM encryption utilities
• SSRF protection on web_fetch
• HMAC-SHA256 mesh authentication