advisory-mining
Mine GitHub Security Advisories and CVE databases for incomplete fixes, finding variant vulnerabilities in patched code or similar patterns in related packages.
Detect Server-Side Request Forgery where user-controlled URLs can reach internal services, cloud metadata endpoints, or bypass network boundaries.
$ npx -y skills add ByamB4/find-cve-agent --skill ssrf --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ssrfContext preview
The summary Claude sees to decide when to auto-load this skill.
Detect Server-Side Request Forgery where user-controlled URLs can reach internal services, cloud metadata endpoints, or bypass network boundaries.
name: ssrf
description: "Detect Server-Side Request Forgery where user-controlled URLs can reach internal services, cloud metadata endpoints, or bypass network boundaries."
metadata:
filePattern:
- "**/*.js"
- "**/*.ts"
- "**/*.py"
- "**/*.go"
- "**/*.rb"
bashPattern:
- "semgrep.*ssrf"
- "grep.*(fetch|axios|requests\\.get|http\\.get)"
priority: 85Audit webhook handlers, URL preview generators, import-from-URL features, image proxy endpoints, PDF generators that fetch remote resources, and any endpoint that makes HTTP requests based on user-supplied URLs.
# JavaScript
grep -rn "fetch(\|axios\|got(\|node-fetch\|http\.get\|https\.get\|request(" .
grep -rn "urllib\|url\.parse\|new URL(" .
# Python
grep -rn "requests\.get\|requests\.post\|urllib\.request\|urlopen\|httpx" .
# Go
grep -rn "http\.Get\|http\.Post\|http\.NewRequest\|httpClient" .
# Ruby
grep -rn "Net::HTTP\|open-uri\|Faraday\|HTTParty\|RestClient" .Trace the URL parameter backwards:
grep -rn "isPrivate\|isInternal\|isLocalhost\|blocked\|allowlist\|blocklist" . grep -rn "127\.0\.0\.1\|0\.0\.0\.0\|169\.254\|10\.\|172\.16\|192\.168" .
Common bypass techniques:
Dangerous protocols beyond http/https:
If the target runs on cloud infrastructure:
Open Source CVE Hunting Harness for Claude Code A Claude Code plugin that systematically finds real CVEs in open source packages through coordinated multi-agent security research.
Repo: ByamB4/find-cve-agent
Mine GitHub Security Advisories and CVE databases for incomplete fixes, finding variant vulnerabilities in patched code or similar patterns in related packages.
Detect authentication and authorization bypass vulnerabilities including missing auth middleware, JWT algorithm confusion, IDOR, and session fixation.
Detect code injection vulnerabilities in packages that dynamically generate or evaluate code via new Function(), eval(), vm.run*, or template literal…
Detect OS command injection via shell execution sinks where user-controlled input reaches system commands without proper sanitization.
Cross-pollination multiplier technique: find a vulnerability in one package, then search for the same pattern across all similar packages to multiply findings.
Detect decompression bomb vulnerabilities where compressed input can expand to exhaust memory, targeting buffer-based decompression without size limits.