agentleFS
zyphr-labszyphr-labs/bounty-harness/.claude/skills/vuln-intel/SKILL.md

vuln-intel

Skill1 starsChanged 3 months agoMITView on GitHub

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We found no rules to list in this file: it reads as prose or reference rather than instructions.

Files
SKILL.md

Vulnerability Intelligence

Overview

Automated vulnerability intelligence gathering for bug bounty targets. Searches NVD, GitHub Security Advisories, disclosed bug bounty reports, proof-of-concept repositories, and security news — then maps findings to technique-kb entries for actionable test plans.

Quick Reference

  • Skill: vuln-intel
  • Version: 1.0.0
  • Bounded Context: VulnIntelContext
  • Required tools: python3, curl
  • Risk tier: passive (read-only API queries, no target interaction)
  • API keys: None required for basic operation

Available Workflows

WorkflowPurposeSafety Tier
search-cvesSearch NVD for CVEs related to targetpassive
search-reportsSearch disclosed bug bounty reportspassive
search-pocsSearch GitHub for proof-of-concept codepassive
search-newsSearch security news about targetpassive
generate-reportFull intelligence report from all sourcespassive
correlate-techniquesMap findings to technique-kb entriespassive

Workflow Selection

IntentWorkflow
Find recent CVEs for targetsearch-cves
Find disclosed reports for programsearch-reports
Find PoCs for specific CVEsearch-pocs
Find security news about targetsearch-news
Full intelligence reportgenerate-report
Map findings to test techniquescorrelate-techniques

Environment Variables

VariableDefaultDescription
INTEL_DAYS60Lookback period for CVEs and news
INTEL_CVSS_MIN0.0Minimum CVSS score filter
INTEL_PLATFORMShackerone,bugcrowdPlatforms to search for disclosed reports
TECHNIQUE_KB_DIR.claude/skills/technique-kb/Path to technique knowledge base

Evidence Required

For every intelligence finding, collect:

  • CVE metadata (ID, description, CVSS, published date, references)
  • Disclosed report metadata (ID, platform, title, URL, bounty amount if known)
  • PoC repository metadata (stars, language, last updated, license)
  • Correlation mapping between CVEs and technique-kb entries
  • Screenshot or archive of source pages (for ephemeral content)
  • Timestamp of search query execution

References

  • NVD API documentation: https://nvd.nist.gov/developers
  • GitHub Security Advisories API
  • OWASP WSTG-INFO-01 (Conduct Search Engine Discovery)
  • OWASP WSTG-INFO-02 (Fingerprint Web Server)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.