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

reporting

Skill1 starsChanged 3 months agoMITView on GitHub

This is a thin human-facing router. Use skill.yaml as the source of truth for exact commands, inputs, outputs, and workflow chaining.

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Start with generate-single unless prior evidence points to a more specific workflow.

    line 16
  2. Very specific:

    Follow each workflow next mapping in skill.yaml after reviewing generated findings.

    line 17
  3. Distinctive:

    If a workflow has no script reference, treat it as a manual or tool-native workflow and use the closest phase runbook when available.

    line 18
  4. Very specific:

    Never submit a report that failed quality-check with errors.

    line 35

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Reporting

Overview

Bug bounty report generation, CVSS scoring, evidence packaging, platform-specific exports

This is a thin human-facing router. Use skill.yaml as the source of truth for exact commands, inputs, outputs, and workflow chaining.

Quick Reference

  • Skill: reporting
  • Severity range: info, low, medium, high, critical
  • Required tools: python3, curl, jq, date
  • Expected input files: findings.jsonl
  • Scope check: confirm authorization before running intrusive or authenticated testing.

Workflow Selection

  • Start with generate-single unless prior evidence points to a more specific workflow.
  • Follow each workflow next mapping in skill.yaml after reviewing generated findings.
  • If a workflow has no script reference, treat it as a manual or tool-native workflow and use the closest phase runbook when available.
  • Runbooks: use runbooks/ and select the closest phase runbook when workflow names do not map 1:1.

Available Workflows

WorkflowPurposeScript pathsPrimary outputsEvidence
generate-singleGenerate a single finding report from evidence.claude/skills/reporting/scripts/report_generator.py$OUTDIR/reports/report.md$OUTDIR/reports/evidence/
cvss-scoreCalculate CVSS v3.1 score for a finding.claude/skills/reporting/scripts/cvss_calc.py$OUTDIR/reports/cvss.json$OUTDIR/reports/evidence/
batch-generateGenerate reports from nuclei/skill JSONL output.claude/skills/reporting/scripts/batch_reporter.py$OUTDIR/reports/summary.md<br>$OUTDIR/reports/findings/$OUTDIR/reports/evidence/
platform-exportRender platform-specific report (HackerOne, Bugcrowd, generic).claude/skills/reporting/scripts/platform_templates.py$OUTDIR/reports/report_<platform>.md$OUTDIR/reports/evidence/
quality-checkGate report for submission readiness (sections, placeholders, secret leaks, evidence).claude/skills/reporting/scripts/quality_gate.py$OUTDIR/reports/quality_report.json$OUTDIR/reports/evidence/
estimate-bountyEstimate bounty range from severity, vuln class, program tier.claude/skills/reporting/scripts/bounty_estimator.py$OUTDIR/reports/bounty_estimate.json$OUTDIR/reports/evidence/
export-bundlePackage findings into share-safe ZIP with manifest (complete vs partial).claude/skills/reporting/scripts/export_bundle.py$OUTDIR/reports/bundle.zip$OUTDIR/reports/evidence/
rank-findingsRe-rank findings by bounty impact using markdown ranker.claude/skills/reporting/scripts/rank_findings.py$OUTDIR/reports/ranked.jsonl$OUTDIR/reports/evidence/

Workflow Selection

  • Standard chain: generate-single → cvss-score → platform-export → quality-check → estimate-bounty → export-bundle → rank-findings.
  • Never submit a report that failed quality-check with errors; warnings are advisory.
  • Set PLATFORM=hackerone|bugcrowd|generic, PROGRAM_TIER=top|established|standard|small|vdp, and optionally SEVERITY, VULN_TYPE, IMPACT_CLASS in the RunContext before running.
  • export-bundle produces a share-safe ZIP (see manifest.json kind complete vs partial). Do not render PoC fields as HTML.
  • rank-findings re-ranks by markdown policy (payloads/severity_ranker_default.md); heuristic is local, --llm sends titles to OpenAI.

Evidence Required

  • Save raw request and response data for each confirmed finding.
  • Include timestamps, affected target, exact workflow name, tool versions, and reproduction steps.
  • Store screenshots or terminal captures in the workflow evidence directory when the workflow defines one.
  • Redact or sanitize any auth headers, session cookies, bearer tokens, and PII in requests/responses before a report leaves the local machine; evidence stays local-only and is never committed (kept under .gitignore).
  • Evidence templates from skill.yaml:
  • cvss: CVSS vector string and breakdown
  • report: Markdown report with all required sections
  • evidence_package: Tar.gz with evidence + reports
  • quality_gate: Checklist results with errors, warnings, and pass verdict
  • bounty_estimate: Estimated USD range with inputs and disclaimer
  • export_bundle: ZIP with manifest.json, findings.json, reports and evidence (share-safe)
  • ranked_findings: Findings reordered by bounty_rank with severity counts

Quality Gate Rules

The quality-check workflow blocks submission on: missing summary/steps/PoC/impact sections, placeholder text (TODO/TBD/[insert ...]), or leaked secret patterns (live keys, tokens, private key blocks). Warnings flag thin sections, missing CVSS, and absent screenshots.

Bounty Estimation Disclaimer

estimate-bounty output is a heuristic range from published program-table patterns. Actual payouts are decided by each program. Use it to prioritize which finding to report first, never as a promise.

Platform Policy Notes

  • HackerOne identity verification (Aug 2026): H1 now requires completed identity verification on the submitting account for bug bounty submissions; API submissions without it are rejected. Any submission path in this toolkit assumes a verified human account behind the persona - never attempt automated account creation or IDV bypass.

References

  • Source of truth: skill.yaml
  • Runbooks: runbooks/
  • OWASP mappings: none listed in skill.yaml.

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.