Bastion — Security Gateway for AI Agents

██████╗  █████╗ ███████╗████████╗██╗ ██████╗ ███╗   ██╗
██╔══██╗██╔══██╗██╔════╝╚══██╔══╝██║██╔═══██╗████╗  ██║
██████╔╝███████║███████╗   ██║   ██║██║   ██║██╔██╗ ██║
██╔══██╗██╔══██║╚════██║   ██║   ██║██║   ██║██║╚██╗██║
██████╔╝██║  ██║███████║   ██║   ██║╚██████╔╝██║ ╚████║
╚═════╝ ╚═╝  ╚═╝╚══════╝   ╚═╝   ╚═╝ ╚═════╝ ╚═╝  ╚═══╝

Type a command. Try: help

Security Gateway for AI Agents

AI agents leak secrets, run blind commands,
and leave no trace. We fix that.

DLP · Prompt Injection Detection · Tool Call Blocking · Full Audit — zero cloud, fully local.

$ npm install -g @aion0/bastion

$ bastion start && bastion wrap claude

✓ dashboard: http://127.0.0.1:8420/dashboard█

════════════════════════════════════════════════════════════════

# SCAN YOUR AGENT

Is your AI agent vulnerable to prompt injection? Find out in 60 seconds.

1 Generate a honeypot URL with hidden attack payloads

2 Ask your agent to read the URL

3 See which attacks succeeded

[ START SCAN ] or type bastion scan your@email.com above

────────────────────────────────────────────────────────────────

# WHAT BASTION CATCHES

🔑 Data Loss Prevention

Scans prompts + responses. 20 patterns: AWS, GitHub, OpenAI, Stripe, private keys, credit cards, SSN, and more.

5 layers: structure → entropy → regex → semantics → ai · action: pass | warn | redact | block

🧬 Prompt Injection Detection

Catches malicious instructions hidden in code comments, READMEs, web content, API responses.

🛡️ Tool Guard

Blocks dangerous tool calls in real-time. 26 rules: rm -rf, curl|bash, eval(), force push, .env read, sudo, and more.

mode: audit | block · streaming support · desktop + webhook alerts

📝 Audit Logger

Every interaction recorded, AES-256-GCM encrypted. Session timeline with security tags. Auto-logged even if disabled.

────────────────────────────────────────────────────────────────

# HOW IT WORKS

  ┌─────────────┐     ┌──────────────────────────────────┐     ┌──────────────┐
  │  AI Agent   │────▶│  B A S T I O N                 │────▶│ LLM Provider │
  │  claude     │     │  DLP → Injection → Guard → Audit │     │  anthropic   │
  │  cursor     │◀────│                                  │◀────│  openai      │
  │  custom     │     │  AI domains: inspect             │     │  google ai   │
  └─────────────┘     │  Everything else: tunnel         │     └──────────────┘
                      └──────────────────────────────────┘

════════════════════════════════════════════════════════════════

Stop flying blind.

[ github ] [ docs ] [ blog ]