CapitalGuard Observatory · Tool record
OpenAI · coding agent
OpenAI Codex can work locally or in cloud environments with repository files, commands, patches, network controls, approvals, plugins, and connected developer workflows.
Public-Control Score
85
Extensive public control coverage
Measures publicly documented control coverage as of the review date. It is not a breach rate, penetration test, endorsement, or guarantee of safety.
Scored dimensions
This record is reviewed against the same five-dimension rubric used across every scored product.
Read MethodologyOfficial material provides extensive operational detail for access and scope transparency.
Official material names concrete controls and meaningful boundaries for data and retention controls.
Official material provides extensive operational detail for connector and permission controls.
Official material provides extensive operational detail for action, approval, and isolation controls.
Official material names concrete controls and meaningful boundaries for audit and administrative evidence.
Documented access points
local repositories and worktrees
commands, patches, tests, and tools
cloud repositories, plugins, MCP servers, and network access
Settings to verify now
Sandbox and approval profile
Writable roots and network policy
Repository, plugin, MCP, and cloud connections
Linked security signals
CVE-2025-59532 · high
Codex CLI 0.2.0 through 0.38.0; affected IDE extension releases before 0.4.12.
Use Codex CLI 0.39.0 or later and IDE extension 0.4.12 or later, then verify the effective writable root before sensitive work.
CGO-CHANGE-2026-06-09 · informational
Supported GitHub agent workflows; coverage depends on repository and agent settings.
Keep the validation enabled, but retain branch protection, review, and least-privilege controls around agent-generated changes.
CGO-RESEARCH-2026-05 · informational
Agentic systems that combine untrusted content, private context, and action-capable tools.
Project trusted provenance, restrict capabilities before generation, and validate outputs before execution.
Linked evidence
Private file access
OpenAI Codex Private File Access: What to Check
Credential exposure
OpenAI Codex API Key Exposure: Check Before You Share
Client confidentiality
OpenAI Codex Client Data Safety for Freelancers
Prompt injection
OpenAI Codex Prompt Injection: A Practical Defense
Connector permissions
OpenAI Codex Connector Permissions: Review the Real Scope
Command execution
OpenAI Codex Command Execution: Keep Control
Unsafe generated code
OpenAI Codex Generated Code Risks: Review Before You Run
History and sharing
OpenAI Codex Chat History and Shared Links: Privacy Check
Accidental oversharing
OpenAI Codex Sensitive Data: What Not to Paste
Autonomous actions
OpenAI Codex Autonomous Actions: Approval Safety Guide
