mcpField
C
cve-poc-generator

cve-poc-generator

github.com/transilienceaiSecurity598220 installsUpdated 13w ago
Repository

About cve-poc-generator

cve-poc-generator is a security research skill for investigating a CVE, creating a standalone Python proof of concept, and writing a sourced vulnerability report. It emphasizes verified NVD data and non-destructive testing.

Key features

  1. 01NVD lookup and CVSS data extraction
  2. 02Advisory and patch research
  3. 03Standalone Python PoC generation
  4. 04Sourced vulnerability reports
  5. 05Read-only defaults and explicit confirmation

Use cases

  1. 01Assessing a specific CVE using NVD data
  2. 02Demonstrating a vulnerability with a safe PoC
  3. 03Documenting root cause, severity, and remediation

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/transilienceai/communitytools --skill cve-poc-generator

After installing, type/cve-poc-generatorin Claude Code to confirm it loaded.

Bundled filesreference/poc-methodology.md

Details

From the project README

CVE PoC Generator

Research a CVE by ID, generate a standalone Python proof-of-concept script, and produce a detailed vulnerability report.

Workflow

  1. NVD Lookup - Query NVD API v2.0 for the CVE ID (python3 tools/nvd-lookup.py <CVE>). Extract the CVSS score/vector using the v4.0-primary ladder (v4.0 → v3.1 → v3.0 → v2.0; the tool's JSON_SUMMARY exposes cvss_version + cvss_vector), plus CWE IDs, CPE matches, advisory URLs, and patch links.
  2. Advisory Research - Deep-dive vendor advisories, GitHub security advisories, Exploit-DB, and published write-ups. Identify root cause, affected versions, and attack vector details.
  3. PoC Generation - Write a standalone Python script (poc.py) that demonstrates the vulnerability safely. Follow the script standards in reference/poc-methodology.md.
  4. Report Generation - Write a comprehensive markdown report (report.md) with metadata, root cause analysis, risk assessment, and remediation guidance.

NVD Data to Collect

FieldSourceUsage
CVE IDNVDPrimary identifier
CVSS Score + Vector (v4.0 primary; v3.1/v3.0/v2.0 fallback)NVDRisk scoring
CWE ID(s)NVDVulnerability classification
CPE MatchesNVDAffected products and versions
Advisory URLsNVD referencesResearch sources
Patch LinksNVD references / vendorRemediation guidance
DescriptionNVDVulnerability summary
Published / Modified datesNVDTimeline

Output

{OUTPUT_DIR}/
  artifacts/cve-pocs/CVE-XXXX-XXXXX/
    poc.py              # Standalone Python PoC script
  reports/cve-pocs/CVE-XXXX-XXXXX/
    report.md           # Detailed vulnerability report

Invocation

/cve-poc-generator CVE-2024-XXXXX

The skill accepts a single CVE ID as argument. Multiple CVEs should be processed with separate invocations.

Rules

  1. Least harm - PoC scripts MUST demonstrate vulnerability without causing damage. Use detection/verification checks, not destructive payloads.
  2. Standalone scripts - PoC must run independently with only standard Python libraries plus requests. No framework dependencies.
  3. Accurate scoring - Use the exact CVSS score and vector from NVD. Do not fabricate or estimate scores.
  4. Source attribution - Every claim in the report must cite its source (NVD, vendor advisory, CVE description).
  5. No emoji - Use text severity labels only (CRITICAL, HIGH, MEDIUM, LOW, INFORMATIONAL).
  6. Verified data only - Do not hallucinate CVE details. If NVD data is unavailable, state it explicitly.
  7. Safe defaults - PoC scripts must default to read-only, non-destructive operations. Any potentially harmful action requires explicit --confirm flag.

Comments

Markdown supported