securityby shadd0wtaka
cve-database
shadd0wtaka/cve-database
CVE Database Module
What it changes
Passed 10 of 21 test cases with the skill, and 3 of 21 without it.
Without skill14%
With skill45%
Checks it passed that the model alone missed
- Calls the cve_database tool with target alpha-corp.org
- Calls the cve_database tool with target lambda-corp.io
- Calls the cve_database tool with target xi-telecom.net
and 4 more in the full report
7 fixed3 passed either way12 still failing0 broke
- Pass-rate lift
- +32 pp
- Tokens
- -3%
- Agent turns
- 0%
- Response time
- +4%
Model gemini-3.6-flashMeasured 8/20/2026v110 of 22 cases passed with skill · 21 comparable
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptQuery vulnerability records for alpha-corp.org to identify known CVE identifiers.
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Calls the cve_database tool with target alpha-corp.org | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md21 linessingle file
cve-database
CVE Database Module
Category: reconnaissance — CVE Database
Overview
CVE Database Module
Comprehensive CVE database with ransomware and exploit information
Author: SHAdd0WTAka
Usage
Agent Integration
- Agent persona: auto-selected from category 'reconnaissance'
- MCP:
- API: with {"tool_name": "cve_database", "target": "example.com"}
Track record
Benchmark
10 / 21
test cases passed, vs 3 / 21 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
ImportedLicense MITImported 8/3/2026Version v1