vex — Claude Code skill: what it does, how to install
OpenVEX v0.2.0 reference and management playbooks for structuring, checking, and validating vulnerability statements.
no license ★ 1,627 updated 2026-10-25
npx skills add microsoft/hve-core --skill vex -a claude-codeWhat vex does
This skill brings OpenVEX v0.2.0 specifications directly into the agent context. It supplies mutation contracts, transition boundaries, and workflow procedures for embedding VEX documents into repository paths under security/vex.
The documentation dictates strict state rules across not_affected, affected, fixed, and under_investigation. Marking an item as not_affected fails validation unless supplied with an approved justification code such as vulnerable_code_not_in_execute_path or an impact explanation. Components are referenced via standard Package URL strings.
Because the configuration sets user-invocable: false, you do not trigger this via a dedicated slash command. The agent reads these procedures automatically when orchestrating security workflows or reviewing exploitability with the CVE Analyzer subagent.
What it helps with
- set up the security/vex repository structure
- validate OpenVEX status transitions against schema rules
- select machine-readable justifications for unaffected components
- prepare pull request scaffolds for VEX release attestations
Example prompts for the agent
- Inspect our OpenVEX document and verify justification codes for unaffected items
- Bootstrap the security/vex directory using the implementation playbook
- Check if changing this vulnerability status violates transition rules
How to install vex
1Skills CLI (Vercel)
npx skills add microsoft/hve-core --skill vex -a claude-code2Manually: put the files in place
~/.claude/skills/vex/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/vex/
1Skills CLI (Vercel)
npx skills add microsoft/hve-core --skill vex -a codex2Manually: put the files in place
.agents/skills/vex/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add microsoft/hve-core --skill vex -a cursor2Manually: put the files in place
.cursor/skills/vex/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install microsoft/hve-core .github/skills/security/vex2Manually: put the files in place
.github/skills/vex/SKILL.md1Skills CLI (Vercel)
npx skills add microsoft/hve-core --skill vex -a gemini-cli2Platform CLI
gemini skills install https://github.com/microsoft/hve-core --path .github/skills/security/vexManually: put the files in place
.devin/skills/vex/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about vex
How to install vex in Claude Code?
Run npx skills add microsoft/hve-core --skill vex -a claude-code in your terminal.
What does the vex skill provide?
It supplies the OpenVEX v0.2.0 schema reference, status decision trees, and management playbooks for vulnerability tracking.
Why is this skill marked as non-invocable?
Its configuration sets user-invocable: false, meaning Claude Code incorporates its rules autonomously during security reviews rather than expecting a direct slash command.