cve-poc-generator

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

CVE PoC Generator

CVE PoC 生成器

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

根据 CVE ID 研究漏洞，生成独立的 Python 概念验证脚本，并产出详细的漏洞报告。

Workflow

工作流

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.
Advisory Research - Deep-dive vendor advisories, GitHub security advisories, Exploit-DB, and published write-ups. Identify root cause, affected versions, and attack vector details.
PoC Generation - Write a standalone Python script (
```
poc.py
```
) that demonstrates the vulnerability safely. Follow the script standards in
```
reference/poc-methodology.md
```
.
Report Generation - Write a comprehensive markdown report (
```
report.md
```
) with metadata, root cause analysis, risk assessment, and remediation guidance.

NVD 查询 - 通过 NVD API v2.0 查询 CVE ID（
```
python3 tools/nvd-lookup.py <CVE>
```
）。使用以 v4.0 为首选的版本阶梯提取 CVSS 分数和向量（v4.0 → v3.1 → v3.0 → v2.0；工具的
```
JSON_SUMMARY
```
会公开
```
cvss_version
```
和
```
cvss_vector
```
），同时提取 CWE ID、CPE 匹配项、公告 URL 和补丁链接。
公告研究 - 深入研究厂商公告、GitHub 安全公告、Exploit-DB 和已发布的漏洞分析文章。识别根本原因、受影响版本及攻击向量细节。
PoC 生成 - 编写一个安全演示漏洞的独立 Python 脚本（
```
poc.py
```
）。遵循
```
reference/poc-methodology.md
```
中的脚本标准。
报告生成 - 编写全面的 Markdown 报告（
```
report.md
```
），涵盖元数据、根本原因分析、风险评估和修复建议。

NVD Data to Collect

需要收集的 NVD 数据

Field	Source	Usage
CVE ID	NVD	Primary identifier
CVSS Score + Vector (v4.0 primary; v3.1/v3.0/v2.0 fallback)	NVD	Risk scoring
CWE ID(s)	NVD	Vulnerability classification
CPE Matches	NVD	Affected products and versions
Advisory URLs	NVD references	Research sources
Patch Links	NVD references / vendor	Remediation guidance
Description	NVD	Vulnerability summary
Published / Modified dates	NVD	Timeline

字段	来源	用途
CVE ID	NVD	主要标识符
CVSS 分数和向量（首选 v4.0；回退至 v3.1/v3.0/v2.0）	NVD	风险评分
CWE ID	NVD	漏洞分类
CPE 匹配项	NVD	受影响的产品和版本
公告 URL	NVD 引用项	研究来源
补丁链接	NVD 引用项/厂商	修复指导
描述	NVD	漏洞摘要
发布/修改日期	NVD	时间线

Output

输出

{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

{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

调用方式

/cve-poc-generator CVE-2024-XXXXX

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

/cve-poc-generator CVE-2024-XXXXX

该 skill 接受单个 CVE ID 作为参数。多个 CVE 应通过单独调用分别处理。

Rules

规则

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

最小危害 - PoC 脚本必须演示漏洞且不得造成破坏。使用检测或验证检查，而非破坏性 payload。
独立脚本 - PoC 必须仅依赖 Python 标准库和
```
requests
```
独立运行。不得依赖框架。
准确评分 - 使用 NVD 中准确的 CVSS 分数和向量。不得编造或估算分数。
来源标注 - 报告中的每项论断都必须引用其来源（NVD、厂商公告、CVE 描述）。
不使用 emoji - 仅使用文本严重性标签（CRITICAL、HIGH、MEDIUM、LOW、INFORMATIONAL）。
仅使用已验证的数据 - 不得编造 CVE 详情。如果 NVD 数据不可用，应明确说明。
安全默认值 - PoC 脚本必须默认采用只读、非破坏性操作。任何可能有害的操作均需显式提供
```
--confirm
```
标志。