ghost-self-audit
100 / 100 · Low risk
Fine to try.
Independent third-party security and architecture audit of the GHOST codebase, produced by GLM (Z.ai) on 2026-11-12 against commit 617e672. Load this skill when the Operator asks about GHOST's own architecture, security posture, code quality, audit findings, or what the outside review found. Contains verified findings with file-level evidence, explicitly retracted findings, and a prioritized remediation list. Not written by the development toolchain and not written by the audited runtime.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'ghost-self-audit' ] || [ -L ~/.agents/skills/'ghost-self-audit' ]; then echo 'A skill folder named ghost-self-audit already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/vNeeL-code/GHOST' "$d" && git -C "$d" checkout --quiet '88b58f773b0597fc34424901314b93cf21cc4f8d' -- 'app/src/main/assets/skills/ghost-self-audit' && mkdir -p ~/.agents/skills && cp -R "$d"/'app/src/main/assets/skills/ghost-self-audit' ~/.agents/skills/'ghost-self-audit' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'ghost-self-audit' ~/.claude/skills/'ghost-self-audit' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/vNeeL-code/GHOST/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-14 | 88b58f7 | 100 |