bug-bounty-report-writing — Claude Code skill: setup and usage
bug-bounty-report-writing guides agents in drafting vulnerability submissions with verified impact and reproduction steps with CVSS scoring. Useful before sending bug reports to bounty programs.
no license 290 installs updated 2026-08-26
npx skills add securityskills/skills --skill bug-bounty-report-writing -a claude-codeWhat bug-bounty-report-writing does
The skill organizes vulnerability disclosures into a clean structure for triage teams. It enforces an asset-focused title, calculated CVSS vectors, reproduction steps, and remediation guidance. Speculative claims about remote execution without clear paths are flagged immediately.
Evidence handling follows strict privacy practices. Any exposed personal details must be redacted from request logs and screenshots before submission. It also warns against common submission mistakes, such as submitting automated scanner dumps or claiming high severity for self-XSS.
Reports must cover a single flaw. Vulnerability chains are allowed only when individual steps have no impact on their own.
What it helps with
- structure reproduction steps so triage teams verify them quickly
- calculate the CVSS score with a complete vector string
- draft clear remediation advice for the asset owner
- redact personal data from proof-of-concept logs and images
Example prompts for the agent
- Help me draft a bug report for a stored XSS issue in the support ticket form
- Generate the CVSS vector string and articulate the exact security impact
- Turn these raw HTTP request logs into clean reproduction steps
How to install bug-bounty-report-writing
1Skills CLI (Vercel)
npx skills add securityskills/skills --skill bug-bounty-report-writing -a claude-code2Manually: put the files in place
~/.claude/skills/bug-bounty-report-writing/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/bug-bounty-report-writing/
1Skills CLI (Vercel)
npx skills add securityskills/skills --skill bug-bounty-report-writing -a codex2Manually: put the files in place
.agents/skills/bug-bounty-report-writing/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add securityskills/skills --skill bug-bounty-report-writing -a cursor2Manually: put the files in place
.cursor/skills/bug-bounty-report-writing/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install securityskills/skills bug-bounty/bug-bounty-report-writing/SKILL.md2Manually: put the files in place
.github/skills/bug-bounty-report-writing/SKILL.md1Skills CLI (Vercel)
npx skills add securityskills/skills --skill bug-bounty-report-writing -a gemini-cli2Platform CLI
gemini skills install https://github.com/securityskills/skills --path bug-bounty/bug-bounty-report-writingManually: put the files in place
.devin/skills/bug-bounty-report-writing/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add securityskills/skills --skill bug-bounty-report-writing -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-report-writing
How do I install bug-bounty-report-writing in Claude Code?
Run npx skills add securityskills/skills --skill bug-bounty-report-writing -a claude-code in your terminal.
What does bug-bounty-report-writing do?
It formats vulnerability reports with severity ratings, verified impacts, step-by-step reproduction instructions, and fix recommendations.
Why do triagers downgrade vulnerability reports?
Ratings drop when reports speculate about damage without practical proof, paste unverified scanner output, or report IDOR without demonstrating two separate accounts.