crtvrffnrt/skills

pentest-evidence-structuring-report-synthesis

Evidence structuring and report synthesis for confirmed findings, severity ranking, remediation guidance, executive summaries, technical appendices, and unresolved evidence gaps. Hands off to live validation workflows when proof is incomplete.

First seen Feb 19, 2026

Installation

$ npx skills add crtvrffnrt/skills --skill pentest-evidence-structuring-report-synthesis

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from crtvrffnrt/skills · top by installs.

npx skills add crtvrffnrt/skills

Browse all from crtvrffnrt/skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 3
Default branch main
Open issues 0
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,959 B
  • docs SUMMARY.md 296 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 49 installs

SKILL.md

Evidence Structuring & Report Synthesis

Use When

  • The task is to consolidate findings, deduplicate evidence, rank severity, write remediation, or create executive and technical deliverables.
  • Live validation is complete or the user explicitly wants unresolved gaps documented.

Handoff Criteria

  • Hand off to the relevant validation skill when exploitability, impact, scope, or control evidence is missing and safe validation is still in scope.

Output Schema

  • Confirmed findings table: id, title, severity, confidence, impact
  • Evidence map: finding id to reproducible proof artifacts
  • Remediation plan: prioritized fixes with verification guidance

Instructions

  1. Separate confirmed findings from hypotheses and informational observations.
  2. Deduplicate by root cause and attacker capability, not by endpoint count alone.
  3. Assign severity from demonstrated impact and exploitability evidence.
  4. Keep technical evidence concise, reproducible, and traceable.
  5. Produce both technical and executive views from the same canonical evidence.
  6. Mark open questions and explicitly state what remains unverified.

Verification Gate

  • Preserve factual precision and reproducibility in every finding.
  • Keep structure stable for machine parsing and downstream tracking.
  • Tie remediation to the broken control and observed exploit path.
  • Base severity on demonstrated impact, exploitability, affected scope, and preconditions.
  • Do not merge unrelated root causes into a single finding.
  • Report unresolved evidence gaps explicitly.
  • Keep executive and technical output aligned to the same evidence base.