propose-security-hardening — Codex skill: purpose and install
This skill turns vulnerability evidence and scan findings into architectural hardening options. Use it when a single-finding patch does not address the wider design.
npx skills add openai/plugins --skill propose-security-hardening -a codexWhat propose-security-hardening does
propose-security-hardening builds structural and architectural security proposals from vulnerability disclosures, incident material, assessment documents, source code, or a completed Codex Security scan. It helps compare meaningful options, show the architecture before and after a change, and prepare an implementation plan for the selected direction.
The skill keeps supplied evidence separate from the derived analysis and does not alter source evidence or sealed artifacts. Its output can cover tradeoffs, migration steps, and an implementation handoff. A Codex Security scan is optional; a set of disclosure documents or supplied findings is enough to begin.
Install it when the problem calls for systemic security changes and an explicit design choice. For one isolated finding that only needs a local patch, this skill is likely more than you need.
What it helps with
- trace systemic causes behind vulnerabilities
- compare architectural hardening options
- map the system before and after a change
- plan migration for a selected security option
- hand off a design proposal for implementation
Example prompts for the agent
- Review these findings and propose structural security hardening options.
- Compare the hardening choices for this vulnerability, show the before-and-after architecture, and draft a migration plan.
- Use the Codex Security scan results to prepare hardening guidance for the final report.
How to install propose-security-hardening
1Skills CLI (Vercel)
npx skills add openai/plugins --skill propose-security-hardening -a codex2Manually: put the files in place
.agents/skills/propose-security-hardening/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add openai/plugins --skill propose-security-hardening -a claude-code2Manually: put the files in place
~/.claude/skills/propose-security-hardening/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/propose-security-hardening/
Manually: put the files in place
.cursor/skills/propose-security-hardening/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install openai/plugins propose-security-hardening2Manually: put the files in place
.github/skills/propose-security-hardening/SKILL.mdPlatform CLI
gemini skills install https://github.com/openai/plugins --path plugins/codex-security/skills/propose-security-hardeningManually: put the files in place
.devin/skills/propose-security-hardening/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set201
The whole set →Similar
Questions about propose-security-hardening
How do I install propose-security-hardening in Codex?
Run npx skills add openai/plugins --skill propose-security-hardening -a codex. The skill file is available at .agents/skills/propose-security-hardening/SKILL.md.
What does propose-security-hardening do?
It turns vulnerability evidence, incident material, assessment documents, source code, or Codex Security scan findings into architectural hardening proposals. The analysis compares tradeoffs, shows before-and-after views, and outlines implementation for the chosen option.
Do I need a Codex Security scan to use it?
No. The skill can work from vulnerability disclosures, supplied findings, incident or assessment documents, PoCs, traces, source code, or a combination of these inputs.
