Skip to main content

Security Overview

Contop follows a defense-in-depth approach with multiple security layers. The system assumes zero trust between components and implements security at every boundary.

Security Philosophy

  • Defense-in-depth — Multiple independent security layers, so a failure in one doesn't compromise the system
  • Zero trust — Every command is classified before execution, regardless of source
  • Local-first — Data stays on your devices; no cloud intermediary for execution
  • Transparent — Every action is logged and visible to the user in real time

Trust Boundaries

Security Layers

LayerPurposeDocumentation
Transport EncryptionDTLS data channels + SRTP videoPairing & Encryption
Command ClassificationEvery command evaluated before executionDual-Tool Evaluator
Sandbox IsolationDangerous commands run in hardened Docker containersDocker Sandbox
Audit TrailEvery tool call logged with timestamps and outcomesAudit Logging
Physical Access ProtectionAway Mode locks the desktop when unattendedAway Mode Security

Threat Model Summary

ThreatMitigation
Unauthorized device accessQR code pairing + biometric auth + token expiration
Man-in-the-middleDTLS/SRTP encryption + certificate fingerprint in QR
Malicious AI commandsDual-Tool Evaluator classifies every command
Destructive actionsUser confirmation required + Docker sandboxing
Credential exposureEnvironment isolation in sandbox
Physical access when awayAway Mode overlay + keyboard hook + PIN protection
LLM prompt injectionSecurity-focused system prompt, tool classification independent of LLM output

Related: Dual-Tool Evaluator · Docker Sandbox · Pairing & Encryption · Audit Logging