knowledge/cve-search/SKILL.md
Enumerate CVEs for a vulnerability class, find credible public PoC references with GitHub preferred, verify collected URLs, and write structured Markdown evidence for downstream use. Use when asked to build or refresh a CVE list, PoC tracker, exploit reference sheet, or vulnerability-type digest from public sources.
npx skillsauth add aeondave/malskill cve-searchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Repeatable workflow for collecting CVEs of a given type, finding the best public PoC reference for each one, verifying the URLs, and writing traceable Markdown output.
Use this skill when the task is to:
Do not use this skill to claim exploitability without evidence. If no public PoC exists, say so explicitly and keep the best authoritative advisory instead.
vuln_type — required vulnerability class or search themetime_range — optional year, date range, or freshness limitdest_file — optional workspace path for the Markdown output; create one if missingpreferred_source — optional source preference; default is githubWrite entries in Markdown using this template:
- **CVE-YYYY-NNNN:** short title
- **Type:** {vuln_type}
- **PoC:** {poc_url or "not found"}
- **Verification:** {verified | redirected | advisory-only | not-checked}
- **Platforms:** {affected product / version / OS build if known}
- **Source:** {primary evidence source}
- **Notes:** {why this PoC or fallback was chosen}
Follow these steps in order. Skip a step only when it is clearly not applicable.
Before searching, make sure the request is concrete enough to execute:
vuln_type into 2–5 search phrasesdest_file is not provided, derive a clear filename from the requestCollect candidate CVEs from authoritative sources first:
Filter candidates by the requested vulnerability class and time range. Prefer exact matches over broad keyword matches.
For each CVE, search sources in this priority order:
Source ranking rules:
tree/ views, or search-result pagesChoose the best link using this order:
If multiple credible PoCs exist, keep the best one in PoC and mention alternates in Notes.
For each CVE, write one Markdown entry to dest_file.
Quality rules:
PoC: not found when no public exploit reference is availableNotes short and evidence-basedWhen shell access is available, verify URLs by extracting them from dest_file, following redirects, and recording the final HTTP result.
Use the command style that matches the environment.
POSIX shell:
grep -Eo "https?://[^ )\]\"]+" "${dest_file}" | sed 's/[),.]$//' | sort -u | \
while IFS= read -r url; do
curl -sS -L -o /dev/null -w '%{http_code} %U\n' "$url" || echo "000 $url";
done > check_${dest_file##*/}_urls_results.txt
PowerShell:
$destFile = $dest_file
$outFile = "check_$([System.IO.Path]::GetFileName($destFile))_urls_results.txt"
Get-Content $destFile |
Select-String -AllMatches 'https?://[^ )\]\"]+' |
ForEach-Object { $_.Matches.Value } |
ForEach-Object { $_.TrimEnd(')', ',', '.') } |
Sort-Object -Unique |
ForEach-Object {
try {
$response = Invoke-WebRequest -Uri $_ -MaximumRedirection 10 -Method Head
"{0} {1}" -f [int]$response.StatusCode, $_
} catch {
$status = if ($_.Exception.Response) { [int]$_.Exception.Response.StatusCode } else { 0 }
"{0} {1}" -f $status, $_
}
} | Set-Content $outFile
Interpretation:
200 usually means the link is directly usable3xx after redirects is acceptable if the final destination is the intended resource404 or 000 means find an alternate PoC or fall back to an advisory and explain whyBefore finishing, confirm that:
PoC field is either a working public reference or not foundVerification or Notespublic PoC found, reference only, and not found.README.md — operator-facing overview, quick usage, and verification example for this skillscripts/ — none; this skill is intentionally procedural rather than script-drivenreferences/ — none currentlyassets/ — none currentlydata-ai
Scoped routing: Linux operator; hosts, sessions, users, services, packages, logs, containers, SSH, network paths, privilege evidence.
development
Offensive methodology for ICS/OT/SCADA environments in authorized industrial penetration testing and red team operations. Use when assessing PLCs, RTUs, HMIs, engineering workstations, historians, or field devices running Modbus, DNP3, EtherNet/IP, S7comm/S7+, Profinet, IEC 60870-5-104, BACnet, or OPC-UA. Covers passive OT network enumeration, protocol-level device interrogation, PLC coil/register read-write attacks, HMI session exploitation, historian and engineering workstation compromise, and safe escalation rules for critical infrastructure scope. Does not cover: general IT network exploitation (network-technique), physical hardware interfaces UART/JTAG/SPI (hardware-technique), wireless sensor network attacks (wireless-technique), RF/SDR signal analysis (hardware-ctf or wireless-technique), or CTF-framed ICS lab tasks (ics-ctf).
tools
Offensive methodology for authorized game security assessments, game client security research, and game-adjacent penetration testing in real-world engagements. Use when assessing game clients for cheating vulnerabilities, testing anti-cheat effectiveness, auditing game server protocols for score manipulation or economic fraud, reverse engineering game DRM or license validation, analyzing game save file protection, or assessing game mod/plugin security. Covers: process memory scanning and manipulation (Cheat Engine methodology), game binary reversing for license and DRM bypass, game network protocol analysis and packet replay, anti-cheat mechanism analysis, save file format reversing and tampering, speed hack and value injection techniques. Does NOT cover: CTF game challenges (game-ctf), game engine source code auditing (web-exploit-technique or vuln-search-technique for the backend), or general binary exploitation (pwn-ctf or reversing-technique).
development
Auth assessment: hardware/embedded methodology; UART/JTAG/SWD/SPI/I2C, firmware extraction, boot/debug paths, embedded OS evidence.