Codex Knowledge Base
Out-of-Band Prompt Injection Defences: What CaMeL, FIDES, and Progent Reveal About Deterministic Agent Security — and How Codex CLI's Sandbox-Approval-Hook Stack Already Implements the Pattern
Out-of-Band Prompt Injection Defences: What CaMeL, FIDES, and Progent Reveal About Deterministic Agent Security — and How Codex CLI’s Sandbox-Approval-Hook Stack Already Implements the Pattern
Forged Reasoning Attacks on Agent Memory: What FARMA Reveals About the Reasoning Store Blind Spot — and How to Wire Provenance Defence in Codex CLI
Forged Reasoning Attacks on Agent Memory: What FARMA Reveals About the Reasoning Store Blind Spot — and How to Wire Provenance Defence in Codex CLI
Balkanised Execution Security: What 39 Papers Reveal About the Fragmented Defence Landscape for Coding Agents — and Where Codex CLI's Stack Stands
Balkanised Execution Security: What 39 Papers Reveal About the Fragmented Defence Landscape for Coding Agents — and Where Codex CLI’s Stack Stands
Graph-Guided Trajectory Repair: What AgentTether Reveals About Diagnosing Agent Failures — and How to Wire Equivalent Recovery into Codex CLI
Graph-Guided Trajectory Repair: What AgentTether Reveals About Diagnosing Agent Failures — and How to Wire Equivalent Recovery into Codex CLI
De-Idealised Benchmarking: What AgentGym2 Reveals About Real-World Agent Readiness — and Where Codex CLI's Architecture Already Closes the Gaps
De-Idealised Benchmarking: What AgentGym2 Reveals About Real-World Agent Readiness — and Where Codex CLI’s Architecture Already Closes the Gaps
Agent Data Injection: What Probabilistic Delimiter Poisoning Reveals About the Trust Boundary Gap — and How Codex CLI's Layered Defences Respond
Agent Data Injection: What Probabilistic Delimiter Poisoning Reveals About the Trust Boundary Gap — and How Codex CLI’s Layered Defences Respond
Visual Codebase Understanding: What Multimodal Repository Graphs Reveal About Token-Efficient Exploration — and How to Wire Hybrid Visual Context into Codex CLI
Visual Codebase Understanding: What Multimodal Repository Graphs Reveal About Token-Efficient Exploration — and How to Wire Hybrid Visual Context into Codex CLI
Verifiable Literate Programming: What VLP's Three-Layer Validation Reveals About Human-in-the-Loop Code Review — and How to Wire Equivalent Gates in Codex CLI
Verifiable Literate Programming: What VLP’s Three-Layer Validation Reveals About Human-in-the-Loop Code Review — and How to Wire Equivalent Gates in Codex CLI
Safety Testing at Scale: What Vera's 1,600 Executable Cases Reveal About Agent Vulnerabilities — and How Codex CLI's Defence Layers Hold Up
Vera-Bench evaluates four production agent frameworks across 124 risk categories with evidence-grounded verification. Codex CLI's sandbox, hooks, and approval architecture provide measurable containment — but multi-channel attacks still breach 95.8%...
Overeager Coding Agents: What 7,500 Benign Runs Reveal About Unauthorised Scope Expansion — and How Codex CLI's Approval and Sandbox Architecture Stops It
Overeager Coding Agents: What 7,500 Benign Runs Reveal About Unauthorised Scope Expansion — and How Codex CLI’s Approval and Sandbox Architecture Stops It