cve-poc-generator
starsforks
How to install cve-poc-generator?
transilienceai/communitytools/cve-poc-generator
$npx -y skills add transilienceai/communitytools --skill cve-poc-generatorCVE research, standalone PoC script and report generation. Given a CVE ID, researches NVD and advisories, generates a safe Python PoC, and writes a detailed vulnerability report.
SKILL.md
| 1 | # CVE PoC Generator |
| 2 | |
| 3 | Research a CVE by ID, generate a standalone Python proof-of-concept script, and produce a detailed vulnerability report. |
| 4 | |
| 5 | ## Workflow |
| 6 | |
| 7 | 1. **NVD Lookup** - Query NVD API v2.0 for the CVE ID. Extract CVSS v3.1 score/vector, CWE IDs, CPE matches, advisory URLs, and patch links. |
| 8 | 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. |
| 9 | 3. **PoC Generation** - Write a standalone Python script (`poc.py`) that demonstrates the vulnerability safely. Follow the script standards in `reference/poc-methodology.md`. |
| 10 | 4. **Report Generation** - Write a comprehensive markdown report (`report.md`) with metadata, root cause analysis, risk assessment, and remediation guidance. |
| 11 | |
| 12 | ## NVD Data to Collect |
| 13 | |
| 14 | | Field | Source | Usage | |
| 15 | |-------|--------|-------| |
| 16 | | CVE ID | NVD | Primary identifier | |
| 17 | | CVSS v3.1 Score + Vector | NVD | Risk scoring | |
| 18 | | CWE ID(s) | NVD | Vulnerability classification | |
| 19 | | CPE Matches | NVD | Affected products and versions | |
| 20 | | Advisory URLs | NVD references | Research sources | |
| 21 | | Patch Links | NVD references / vendor | Remediation guidance | |
| 22 | | Description | NVD | Vulnerability summary | |
| 23 | | Published / Modified dates | NVD | Timeline | |
| 24 | |
| 25 | ## Output |
| 26 | |
| 27 | ``` |
| 28 | {OUTPUT_DIR}/ |
| 29 | artifacts/cve-pocs/CVE-XXXX-XXXXX/ |
| 30 | poc.py # Standalone Python PoC script |
| 31 | reports/cve-pocs/CVE-XXXX-XXXXX/ |
| 32 | report.md # Detailed vulnerability report |
| 33 | ``` |
| 34 | |
| 35 | ## Invocation |
| 36 | |
| 37 | ``` |
| 38 | /cve-poc-generator CVE-2024-XXXXX |
| 39 | ``` |
| 40 | |
| 41 | The skill accepts a single CVE ID as argument. Multiple CVEs should be processed with separate invocations. |
| 42 | |
| 43 | ## Rules |
| 44 | |
| 45 | 1. **Least harm** - PoC scripts MUST demonstrate vulnerability without causing damage. Use detection/verification checks, not destructive payloads. |
| 46 | 2. **Standalone scripts** - PoC must run independently with only standard Python libraries plus `requests`. No framework dependencies. |
| 47 | 3. **Accurate scoring** - Use the exact CVSS score and vector from NVD. Do not fabricate or estimate scores. |
| 48 | 4. **Source attribution** - Every claim in the report must cite its source (NVD, vendor advisory, CVE description). |
| 49 | 5. **No emoji** - Use text severity labels only (CRITICAL, HIGH, MEDIUM, LOW, INFORMATIONAL). |
| 50 | 6. **Verified data only** - Do not hallucinate CVE details. If NVD data is unavailable, state it explicitly. |
| 51 | 7. **Safe defaults** - PoC scripts must default to read-only, non-destructive operations. Any potentially harmful action requires explicit `--confirm` flag. |
People who liked this also viewed
6 picksType
- entra-app-registrationGuides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API perSkillsJul 2026
- azure-complianceRun Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: SkillsJul 2026
- azure-rbacOfficial agent plugin providing skills and MCP server configurations for Azure scenarios.SkillsJul 2026
- better-auth-best-practicesAgent skill from better-auth/skillsSkillsJul 2026
- firebase-security-rules-auditorA skill to evaluate how secure Firestore security rules are. Use this when Firestore security rules are updated to ensure that the generated rules are extremely secure and robust.SkillsJul 2026
- audit-websiteAudit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility, and 15 other rule categories (260+ rules), returns an LLM-opSkillsJul 2026
