Ghost Report

This aggregates results from Ghost's three security scanners (dependencies, secrets, and code) into a single prioritized markdown report. It reads findings from each scan type, filters for high-confidence issues only (confirmed exploitable deps, verified code flaws, non-rejected secrets), then sorts by severity and inlines all the details so you get one complete document instead of hunting through individual finding files. The filtering logic is opinionated in a good way: it skips unverified dependency vulns and rejected secrets entirely, which cuts noise. Use it when you want the executive summary after running multiple scans, or when you need to hand off a security audit without explaining the toolchain. It caches reports per commit, so re-running is instant.

GitHub stars: 386
last updated: Mar 11, 2026

View on GitHub

Install

$ npx -y skills add ghostsecurity/skills --skill ghost-report --agent claude-code

Installs into .claude/skills of the current project.

Files

Combined Security Report

You aggregate findings from all scan skills (scan-deps, scan-secrets, scan-code) into a single prioritized report. Do all work yourself — do not spawn subagents or delegate.

$ARGUMENTS

Step 0: Setup

Run this Bash command to compute paths:

repo_name=$(basename "$(pwd)") && remote_url=$(git remote get-url origin 2>/dev/null || pwd) && short_hash=$(printf '%s' "$remote_url" | git hash-object --stdin | cut -c1-8) && repo_id="${repo_name}-${short_hash}" && short_sha=$(git rev-parse --short HEAD 2>/dev/null || date +%Y%m%d) && ghost_repo_dir="$HOME/.ghost/repos/${repo_id}" && scans_dir="${ghost_repo_dir}/scans/${short_sha}" && cache_dir="${ghost_repo_dir}/cache" && skill_dir=$(find . -path '*/skills/report/SKILL.md' 2>/dev/null | head -1 | xargs dirname) && echo "scans_dir=$scans_dir cache_dir=$cache_dir skill_dir=$skill_dir"

Store scans_dir (commit-level scan directory), cache_dir, and skill_dir.

Cache Check

If <scans_dir>/report.md already exists, show:

Combined security report is at: <scans_dir>/report.md

And stop. Do not regenerate it.

Step 1: Read Repo Context

SKILL.md on GitHub

Details

Repository: github.com/ghostsecurity/skills
Categories: Security, Productivity & Planning
License: Apache-2.0
First seen: Jun 11, 2026

More from ghostsecurity/skills

All 14