bug-bounty-recon-pipeline — Claude Code skill
bug-bounty-recon-pipeline is a skill that outlines a five-stage bug bounty reconnaissance pipeline, from subdomain enumeration and service fingerprinting to attack-surface change tracking.
no license 288 installs updated 2026-08-26
npx skills add securityskills/skills --skill bug-bounty-recon-pipeline -a claude-codeWhat bug-bounty-recon-pipeline does
The skill describes a continuous pipeline that surfaces new targets as they emerge. Start by ingesting the program scope and validating every host against in-scope rules—nothing slips through on memory alone. Next comes subdomain discovery: passive methods via certificate logs and DNS sources, then active bruteforce and DNS permutations. Each discovered host gets probed with httpx for status, title, and tech stack.
Stage three hunts for URLs via multiple aggregators and looks for high-value patterns: API endpoints, login portals, admin panels, GraphQL, .git, .env. Stage four runs port and service scans with nmap, flagging non-HTTP services like RDP or databases. The final stage re-runs on a schedule and diffs the results, alerting on new hosts, ports, or endpoints.
Critical: automated scanning works only from a VPS or VPN and must align with the program's policy. Aggressive rate-limiting is non-negotiable—many programs block or ban rapid traffic. The skill recommends containerised tooling to keep versions consistent across runs.
What it helps with
- enumerate all subdomains under a target domain and filter by scope rules
- discover open ports and running services on each host
- locate high-value endpoints, APIs, and suspected entry points
- detect new or changed assets between scheduled scan cycles
- collect screenshots and technology stacks for manual review
Example prompts for the agent
- Set up a recon pipeline for a bug bounty target on example.com with daily updates
- Run passive and active subdomain enumeration, then probe each result with httpx for live service detection
- Find risky endpoints like admin panels, APIs, and version-control leaks, then compare with the last scan to spot new attack surface
How to install bug-bounty-recon-pipeline
1Skills CLI (Vercel)
npx skills add securityskills/skills --skill bug-bounty-recon-pipeline -a claude-code2Manually: put the files in place
~/.claude/skills/bug-bounty-recon-pipeline/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/bug-bounty-recon-pipeline/
1Skills CLI (Vercel)
npx skills add securityskills/skills --skill bug-bounty-recon-pipeline -a codex2Manually: put the files in place
.agents/skills/bug-bounty-recon-pipeline/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add securityskills/skills --skill bug-bounty-recon-pipeline -a cursor2Manually: put the files in place
.cursor/skills/bug-bounty-recon-pipeline/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install securityskills/skills bug-bounty/bug-bounty-recon-pipeline/SKILL.md2Manually: put the files in place
.github/skills/bug-bounty-recon-pipeline/SKILL.md1Skills CLI (Vercel)
npx skills add securityskills/skills --skill bug-bounty-recon-pipeline -a gemini-cli2Platform CLI
gemini skills install https://github.com/securityskills/skills --path bug-bounty/bug-bounty-recon-pipelineManually: put the files in place
.devin/skills/bug-bounty-recon-pipeline/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add securityskills/skills --skill bug-bounty-recon-pipeline -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about bug-bounty-recon-pipeline
How do I install bug-bounty-recon-pipeline in Claude Code?
Run npx skills add securityskills/skills --skill bug-bounty-recon-pipeline -a claude-code, then open ~/.claude/skills/bug-bounty-recon-pipeline/SKILL.md in your editor.
What does this skill do?
It outlines a five-stage reconnaissance pipeline: scope validation, subdomain enumeration, URL and endpoint discovery, port scanning, and change detection. Output is a prioritised list of new or modified assets, annotated with observed technologies and suspected vulnerabilities.
Do I need permission to run this against a bounty target?
Yes. Always verify that the program allows automated scanning and stay within their scope rules. Run only from an approved VPN or VPS and apply rate-limiting to avoid triggering blocks or bans.