Skip to content

Security Architecture

OpenParallax implements the Parallax security paradigm: the system that reasons cannot execute, the system that executes cannot reason, and an independent validator sits between them. This is structural enforcement, not behavioral — it does not depend on the model's safety training, the prompt, or runtime checks the model could bypass.

This section documents every security mechanism in the system, organized by what category of threat each one mitigates.

Defense Mechanism Map

GroupMechanismsWhat it protects against
Structural IsolationCognitive-executive separation, kernel sandbox, sub-agent recursion guardA compromised LLM directly executing harmful actions
Action ValidationShield (4 tiers), safe-command fast path, protection layer, denylist, IFC, hash verifierHarmful tool calls proposed by the LLM reaching execution
State ProtectionChronicle, audit chain, memory isolation, OTR modeUnrecoverable state corruption, evidence tampering, data persistence leaks
Input/Output SafetyOutput sanitization, redaction, SSRF protection, HTTP header denylist, git flag injection prevention, tool call ID sanitization, identity validation, Ollama loopback restriction, setup wizard allowlistPrompt injection, data exfiltration, credential leakage
Resource LimitingRate limit, Tier 2 budget, verdict TTL, Tier 3 hourly cap, crash budget, sub-agent caps, reasoning loop roundsResource exhaustion, runaway loops, denial of service
Cryptographic FoundationsAction hashing, canary tokens, agent auth token, audit hash chainTampering, impersonation, replay attacks

Configurable vs Non-Negotiable

Some mechanisms are structurally fixed in the compiled binary — they cannot be disabled via configuration, environment variables, or any runtime API. Others have tunable parameters (policy presets, rate limits, budgets) while the mechanism itself remains active.

See Non-Negotiable Defenses for the full inventory of fixed mechanisms, and Hardening for the tuning guide.

Threat Model

The Threat Model maps each defense to specific threats from OWASP Top 10, OWASP Top 10 for LLM Applications, MITRE ATLAS, and CWE.

Information Flow Control

The IFC reference documents the policy-driven data classification and flow control system that prevents sensitive data from crossing sensitivity boundaries.