Hopeids

# hopeIDS Security Skill

Inference-based intrusion detection for AI agents with quarantine and human-in-the-loop.

## Security Invariants

These are **non-negotiable** design principles:

1. **Block = full abort** — Blocked messages never reach jasper-recall or the agent
2. **Metadata only** — No raw malicious content is ever stored
3. **Approve ≠ re-inject** — Approval changes future behavior, doesn't resurrect messages
4. **Alerts are programmatic** — Telegram alerts built from metadata, no LLM involved

---

## Features

- **Auto-scan** — Scan messages before agent processing
- **Quarantine** — Block threats with metadata-only storage
- **Human-in-the-loop** — Telegram alerts for review
- **Per-agent config** — Different thresholds for different agents
- **Commands** — `/approve`, `/reject`, `/trust`, `/quarantine`

---

## The Pipeline

```
Message arrives
    ↓
hopeIDS.autoScan()
    ↓
┌─────────────────────────────────────────┐
│  risk >= threshold?                     │
│                                         │
│  BLOCK (strictMode):                    │
│     → Create QuarantineRecord           │
│     → Send Telegram alert               │
│     → ABORT (no recall, no agent)       │
│                                         │
│  WARN (non-strict):                     │
│     → Inject <security-alert>           │
│     → Continue to jasper-recall         │
│     → Continue to agent                 │
│                                         │
│  ALLOW:                                 │
│     → Continue normally                 │
└─────────────────────────────────────────┘
```

---

## Configuration

```json
{
  "plugins": {
    "entries": {
      "hopeids": {
        "enabled": true,
        "config": {
          "autoScan": true,
          "defaultRiskThreshold": 0.7,
          "strictMode": false,
          "telegramAlerts": true,
          "agents": {
            "moltbook-scanner": {
              "strictMode": true,
              "riskThreshold": 0.7...