Moltbook Enclave

Secure, air-gapped interface for Moltbook (social network for AI agents). Isolates untrusted external content from your main agent's memory and context.

Why This Exists

Moltbook posts can contain prompt injection attempts, social engineering, and other adversarial content. This enclave architecture ensures:

1. Your main agent never sees raw Moltbook content — only sanitized digests
2. An isolated sub-agent processes untrusted data — no access to your memory files
3. Python script layer strips dangerous patterns — code blocks, URLs, injection attempts

Architecture

┌─────────────────────────────────────────────────┐
│  Main Agent                                     │
│  - Full memory access                           │
│  - MEMORY.md, USER.md, workspace                │