Skip to main content
skill CX Codex

cvss-scoring — Claude Code skill: CVSS v4.0 vectors

The cvss-scoring Claude Code skill turns a vulnerability description into a CVSS v4.0 vector. It activates for requests to score a finding or estimate its severity.

CC-BY-SA-4.0 304 installs ★ 8,341 updated 2026-10-24

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add trailofbits/skills --skill cvss-scoring -a claude-code
Open on GitHub

What cvss-scoring does

The skill reads a vulnerability description and builds a CVSS v4.0 vector string. It first gathers facts about access, attacker privileges, conditions, and impact, then evaluates the metrics in sequence. When key exploitability details are unclear, it asks for clarification; ambiguous impact values are marked as assumptions.

The output includes a FIRST.org calculator link with the vector filled in. The skill does not calculate the numeric score; the calculator does. Metric definitions are read from references/metrics.md. CVSS v3.1 scoring, deployment-specific risk, and issues without an exploitable security impact fall outside its scope.

What it helps with

  • create a CVSS v4.0 vector from a vulnerability report
  • identify missing facts about how an attack works
  • assess the impact of a security weakness
  • compare the severity of vulnerability findings

Example prompts for the agent

  • Score this remotely exploitable server flaw using CVSS v4.0.
  • Build a CVSS v4.0 vector for this finding and ask about any missing attack details.
  • Compare these findings using the CVSS v4.0 metrics.

How to install cvss-scoring

1Skills CLI (Vercel)

npx skills add trailofbits/skills --skill cvss-scoring -a claude-code

2Manually: put the files in place

~/.claude/skills/cvss-scoring/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/cvss-scoring/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about cvss-scoring

How do I install cvss-scoring in Claude Code?

Run npx skills add trailofbits/skills --skill cvss-scoring -a claude-code. The skill file is at ~/.claude/skills/cvss-scoring/SKILL.md.

What does cvss-scoring do?

It derives a CVSS v4.0 vector from a vulnerability description and provides a FIRST.org calculator link with that vector. The skill leaves the numeric score to the calculator.

What is needed to get a numeric CVSS score?

Use the FIRST.org calculator. The skill supplies a link with the generated vector already entered, and the calculator returns the numeric score.

Similar skills

All skills for Security →

From the same set95

The whole set →
prove-patch prove-patch — a skill for Claude Code validates a local security patch with scoped cases and a three-arm comparison. It runs when a patch commit needs independent proof. CX Codex +1 676installs hunt-regressions hunt-regressions — a skill for Claude Code that discovers potential regressions before reproduction. Runs when analyzing code changes and their callers. CX Codex +1 675installs reproduce-regression The reproduce-regression Claude Code skill reproduces a regression candidate on live systems before and after a change. It builds a PoC and compares both versions using the same input. CX Codex +1 671installs report-regressions report-regressions — a skill for Claude Code builds regression reports from saved campaign decisions and links findings to evidence. It runs when a campaign report is created or refreshed. CX Codex +1 670installs prepare-regression prepare-regression — a skill for Claude Code that pins source revisions and gathers commit or PR context for a regression investigation. It runs during investigation setup. CX Codex +1 670installs adjudicate-regression adjudicate-regression — a skill for Claude Code and Codex that reviews reproduction evidence to confirm whether a flaw is a true regression or an exclusion. It evaluates live artifacts before logging issues. CX Codex +1 669installs replay-regression The replay-regression Claude Code skill independently tests a supplied PoC against fresh builds from before and after a change. It runs the same input on S0 and S1, then records what happened. CX Codex +1 668installs taint-trace The taint-trace Claude Code skill adjusts a project's static taint-analysis models, then runs its analyzer. It addresses missed data paths, unresolved framework calls, and false positives caused by imprecise models. CX Codex +1 130installs

Project sponsors

Companies that keep this analytics open