Official Technical Resources: OpenAI (page 13)
Official Technical Resources · OpenAI: 258 entries in total; this page lists entries 181–195.
Codex Security TypeScript SDK
Run Codex Security scans from TypeScript, select targets, inspect results, and manage scan lifecycle.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Coding Tools · Model Deployment Options
Link last checked: 2026-09-24
Improving the threat model
Refine the Codex Security context that ranks findings and helps you review faster
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · AI Guardrails
Link last checked: 2026-09-24
Propose security hardening
Develop evidence-backed structural security improvements, compare tradeoffs, and prepare an implementation handoff.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · AI Guardrails
Link last checked: 2026-09-24
Review code changes for security
Review pull requests and local changes for security regressions manually or in CI/CD.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · AI Guardrails
Link last checked: 2026-09-24
Run Codex Security in CI
Scan pull-request and merge-request changes, preserve structured results, upload SARIF, and set a severity policy.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · AI Guardrails
Link last checked: 2026-09-24
Site tools
Use WebMCP to give AI agents a direct way to work with your website
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Context Protocol (MCP) · Tool Calling
Link last checked: 2026-09-24
Windows sandbox
Configure and troubleshoot the native Codex sandbox on Windows
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · AI Guardrails
Link last checked: 2026-09-24
Plugin UI reference (Markdown)
Schema and API fields for tools, resources, and components.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · AI Guardrails
Link last checked: 2026-09-24
Plugin guidelines
Requirements for MCP servers and optional UI in published plugins.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · AI Guardrails
Link last checked: 2026-09-24
Authentication
Authentication patterns for plugin MCP servers.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Guardrails · Agent Identity, Authorization, and Secrets
Link last checked: 2026-09-24
Build an MCP server
Add live data and controlled tools to your plugin.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Context Protocol (MCP) · Tool Calling
Link last checked: 2026-09-24
Build skills
Add repeatable workflows around your plugin's MCP tools.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Context Protocol (MCP) · Tool Calling
Link last checked: 2026-09-24
Package your plugin
Assemble skills and MCP server dependencies into a distributable plugin.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Context Protocol (MCP) · Tool Calling
Link last checked: 2026-09-24
Plugin architecture
Understand how plugins combine skills, MCP servers, and optional UI.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Context Protocol (MCP) · Tool Calling
Link last checked: 2026-09-24
Connect and test your plugin
Test an optional MCP server, then package and evaluate the complete plugin.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Evaluation and Benchmarks · LLM Application Evaluation
Link last checked: 2026-09-24