Skip to main content
skill CX Codex

report-writer — Claude Code skill: security reports and installation

report-writer turns vulnerability findings into bug bounty submissions, penetration test reports, or technical write-ups. Use it when findings need clear evidence, impact, and remediation.

no license ★ 1,298 updated 2026-06-12

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add H-mmer/pentest-agents --skill report-writer -a claude-code
Open on GitHub

What report-writer does

The skill structures security findings as a bug bounty submission, a penetration test report, or a technical write-up. It covers impact, reproduction steps, remediation, and supporting references. OWASP, CWE, and CVE identifiers can be included where relevant.

Before drafting, it calls for reviewing related disclosed reports with search_writeups and get_writeup, then reading rules/mistakes.md. Report sections cover the affected host, vulnerable component, test account, CVSS details, and supporting material. That means a useful draft depends on concrete evidence and details about the finding.

For bug bounty submissions, the instructions name CVSS 4.0, while the version depends on the platform: HackerOne uses 3.1 in the guidance. The skill also cautions against presenting unverified scope as confirmed and against assigning CWE-200 as the primary weakness.

What it helps with

  • turn a vulnerability finding into a bug bounty submission
  • organize penetration test findings by severity
  • document impact and exact reproduction steps
  • draft a technical account of a vulnerability disclosure

Example prompts for the agent

  • Turn this finding into a bug bounty submission with reproduction steps and impact.
  • Build a penetration test report from findings/, ordered by severity.
  • Write a technical account of this vulnerability and include a remediation recommendation.

How to install report-writer

1Skills CLI (Vercel)

npx skills add H-mmer/pentest-agents --skill report-writer -a claude-code

2Manually: put the files in place

~/.claude/skills/agent-report-writer/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/agent-report-writer/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about report-writer

How do I install report-writer in Claude Code?

Run npx skills add H-mmer/pentest-agents --skill agent-report-writer -a claude-code. The skill file is at ~/.claude/skills/agent-report-writer/SKILL.md.

What does report-writer do?

It formats vulnerability findings as bug bounty submissions, penetration test reports, or technical write-ups. Reports cover impact, reproduction, and suggested fixes.

What evidence should I prepare for a vulnerability report?

Prepare details about the affected component, reproducible test steps, and supporting material. The report structure includes PoC references, screenshots, and the test account.

Similar skills

All skills for Security →

From the same set43

The whole set →
pentest-agents-payloads-7 The pentest-agents-payloads-7 rule for Claude Code provides test scenarios for SSRF, parameter injection, prototype pollution, and OAuth flaws during web security audits. CX Codex +1 ★ 1,298repo stars pentest-agents-payloads-1 pentest-agents-payloads-1 is a Claude Code rule that loads an XSS payload reference for pentesting, from basic vectors to WAF bypass via stacked encoding. CX Codex +1 ★ 1,298repo stars pentest-agents-payloads-4 pentest-agents-payloads-4 is a Claude Code rule with examples for reviewing web vulnerabilities, from JWT and deserialization to GraphQL and OAuth. It supports application security assessments. CX Codex +1 ★ 1,298repo stars pentest-agents-chain-table pentest-agents-chain-table is a Claude Code rule that directs security audit agents to chain verified vulnerabilities into exploit paths. CX Codex +1 ★ 1,298repo stars sast-danger-mapper sast-danger-mapper catalogs hazardous source code operations using pattern matching without speculating on exploitability. CX Codex +1 ★ 1,298repo stars sast-danger-mapper sast-danger-mapper — a subagent that finds dangerous operations in source files: memory handling, type casts, arithmetic at trust boundaries, resource deallocation. CX Codex +1 ★ 1,298repo stars report-writer The report-writer subagent for Claude Code compiles vulnerability findings into reports for pentests, bounty submissions, and technical writeups. CX Codex +1 ★ 1,298repo stars sast-gap-analyzer sast-gap-analyzer analyzes traced data flows to uncover validation gaps in source code. Catches incomplete boundary checks, type mismatches, and race conditions before risky operations. CX Codex +1 ★ 1,298repo stars

Project sponsors

Companies that keep this analytics open