Skip to main content
skill CX Codex

cve-risk-score — Claude Code skill: CVE lookup and install

The cve-risk-score skill looks up CVE records in NVD and reports CVSS score, severity, CWE, and description. It runs when a CVE ID appears in the conversation.

MIT 185 installs ★ 632 updated 2026-07-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add transilienceai/communitytools --skill cve-risk-score -a claude-code
Open on GitHub

What cve-risk-score does

When a CVE ID appears in a message or scan output, the skill passes it to tools/nvd-lookup.py for an NVD lookup. Results appear inline for a single vulnerability or in a Markdown table for several. The agent then returns to the original task, using the lookup as supporting context.

The script requires Python 3. Set NVD_API_KEY in .env for the script to use the key and access higher request limits; unauthenticated bulk requests may be throttled by NVD. The skill reports NVD’s returned data rather than estimating a score. If NVD cannot be reached or has not scored a CVE, the result reflects that.

What it helps with

  • look up a CVSS score for a mentioned CVE
  • show a vulnerability’s severity and CWE
  • compare several CVE records in a table
  • add NVD context to code-scanning findings

Example prompts for the agent

  • Look up CVE-2024-12345 in NVD and report its score, severity, and CWE.
  • Put the NVD results for these CVEs in a table, then continue reviewing the findings.
  • Add the NVD description and risk score for the CVE found in this scan.

How to install cve-risk-score

1Skills CLI (Vercel)

npx skills add transilienceai/communitytools --skill cve-risk-score -a claude-code

2Manually: put the files in place

~/.claude/skills/cve-risk-score/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/cve-risk-score/

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

Questions about cve-risk-score

How do I install cve-risk-score in Claude Code?

Run npx skills add transilienceai/communitytools --skill cve-risk-score -a claude-code. The skill file is at ~/.claude/skills/cve-risk-score/SKILL.md.

What does cve-risk-score do?

It looks up CVE IDs in NVD and displays their CVSS score, severity, CWE, and description. Multiple results are presented in a table.

Do I need an API key to look up CVEs?

No key is required. If NVD_API_KEY is set in .env, the script uses it for higher request limits; NVD may throttle bulk requests without a key.

Source text

SKILL.md · MIT
---
name: cve-risk-score
description: Retrieve CVE risk scores from NVD. Auto-invoked whenever a CVE ID is mentioned to display CVSS score, severity, CWE, and description.
---

# CVE Risk Score

Fetch and display CVE risk scores from the National Vulnerability Database (NVD) whenever a CVE ID appears in conversation.

## Trigger

This skill MUST be invoked automatically whenever a CVE ID (pattern `CVE-YYYY-NNNNN`) is mentioned by the user or discovered during research/scanning. Do not wait for explicit invocation.

## Workflow

1. **Extract CVE IDs** from the user's message or tool output (regex: `CVE-\d{4}-\d{4,}`)
2. **Run the lookup script**:
   ```bash
   python3 tools/nvd-lookup.py CVE-XXXX-XXXXX [CVE-YYYY-YYYYY ...]
   ```
3. **Present the results** in a concise table format:

   | CVE ID | Score | Severity | CWE | Description |
   |--------|-------|----------|-----|-------------|
   | CVE-XXXX-XXXXX | 9.8 | CRITICAL | CWE-79 | ... |

4. **Continue with the user's original task** — the score lookup is supplementary context, not a blocking step.

## Output Format

When presenting CVE risk scores inline, use this compact format:

```
CVE-2024-12345: 9.8 CRITICAL (CWE-79) — Remote code execution via ...
```

For multiple CVEs, use a markdown table.

## Rules

1. **Always invoke** — every CVE ID mentioned triggers a lookup. No exceptions.
2. **Non-blocking** — fetch scores in parallel with other work when possible.
3. **Accurate data only** — display exactly what NVD returns. Never estimate or fabricate scores.
4. **Graceful degradation** — if NVD is unreachable or the CVE has no score yet, say so explicitly (e.g., "Not yet scored by NVD").
5. **Rate limiting** — the script handles rate limits internally. For bulk lookups (5+), warn that NVD throttles unauthenticated requests.
6. **API key** — if `NVD_API_KEY` is set in `.env`, the script uses it for higher rate limits.

## Integration

This skill complements other skills:
- **cve-poc-generator**: After seeing the risk score, the user may want a full PoC and report
- **reconnaissance / source-code-scanning**: When these skills discover CVEs in dependencies, auto-lookup their scores
- **coordination**: CVE scores inform priority and severity classification in findings

© transilienceai · MIT · transilienceai/communitytools

Similar skills

All skills for Security →
tooluniverse-polygenic-risk-score mims-harvard tooluniverse-polygenic-risk-score is a Claude Code skill that builds and interprets polygenic risk scores from GWAS, including variant selection, weighting, and independent-cohort validation. CX Codex +1 355installs cve-mcp-server-security-intelligence reason-machines cve-mcp-server-security-intelligence — a skill that runs a local MCP server and hands the agent 27 tools for CVE work: CVSS and EPSS scores, CISA KEV status, exploit hunting and a composite risk score. CX Codex +1 229installs cve-threat-intel mrhlaingbwardev The cve-threat-intel Claude Code skill finds recent CVEs and searches for public PoCs. It activates on requests about new vulnerabilities, exploits, or threats affecting a specific product. CX Codex +1 ★ 326repo stars sbom-cyclonedx-and-cve-reachability-tooling W4L33Dx sbom-cyclonedx-and-cve-reachability-tooling is a Claude Code skill that builds CycloneDX/SPDX validators and vulnerability ranking pipelines. Activates when developing SCA and CVE triage tools. CX Codex +1 ★ 73repo stars CVE Analyzer microsoft CVE Analyzer — a subagent for deep CVE analysis: checks if vulnerable code is reachable in the project and returns evidence-backed VEX status. CX Codex +1 ★ 1,627repo stars EchelonGraph CVE & Exposure echelongraph EchelonGraph CVE & Exposure is an MCP server for Claude Code that checks vulnerabilities across NVD, KEV, and EPSS and assesses network exposure using Shodan. It helps audit SBOM files and lockfile dependencies. CX Codex +1 ★ 25repo stars

From the same set42

The whole set →
github-workflow The github-workflow skill brings GitHub operations to your AI assistant: branches, commits, pushes, pull requests, issues, and code review. Handy when you ask your agent to commit changes, push code, create a PR, or manage branches. CX Codex +1 195installs mobile-security mobile-security is a Claude Code skill that assesses Android and iOS apps against OWASP MASVS/MASTG through artifact review, runtime tests, and privacy checks. CX Codex +1 194installs system Skill for system-level security testing: Active Directory attacks, privilege escalation on Linux and Windows, exploit development. Built for penetration testers and security researchers. CX Codex +1 194installs firewall-review firewall-review is a Claude Code skill for auditing firewall configurations and producing an evidence-based report. It handles ruleset reviews, including FortiGate checks. CX Codex +1 186installs script-generator script-generator generates optimized, syntax-checked Python, Bash, and PowerShell scripts. It builds and validates the files but never executes them. CX Codex +1 176installs skill-update skill-update generates skill directory structure, validates against Anthropic best practices, and enforces line count limits per file. Use when creating or updating a skill. CX Codex +1 174installs risk-prioritiser risk-prioritiser is a Claude Code skill that ranks confirmed attack paths by exploit feasibility, CVSS severity, and business impact. It runs after the attack-path graph is built and when a validated finding reaches nvd.score >= 9.0. CX Codex +1 168installs cryptography cryptography is a Claude Code skill for practical cryptanalysis in CTF challenges and pentests, including lattice attacks, padding oracles, and custom cipher breaks. CX Codex +1 165installs

Project sponsors

Companies that keep this analytics open