← All skills

unsafe-sandbox

100 / 100 · Low risk

Fine to try.

By KalarisLabs/Skill-Doctor (GitHub) · security · 14 stars · scanned at commit 9413620

Rules for unsafe Rust and the L3 behavioral process harness. Use when adding unsafe blocks, FFI, sandbox features, differential replay, or canary credentials.

Works with any agent that supports SKILL.md skills.

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/'unsafe-sandbox' ] || [ -L ~/.agents/skills/'unsafe-sandbox' ]; then echo 'A skill folder named unsafe-sandbox already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/KalarisLabs/Skill-Doctor' "$d" && git -C "$d" checkout --quiet '9413620ade5c7de07e832db43300c6a3ad2f033b' -- 'skills/unsafe-sandbox' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/unsafe-sandbox' ~/.agents/skills/'unsafe-sandbox' && 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/'unsafe-sandbox' ~/.claude/skills/'unsafe-sandbox' (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

The badge for KalarisLabs/Skill-Doctor shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/KalarisLabs/Skill-Doctor.svg)](https://zalavijaysinh.github.io/skilltrust/repos/KalarisLabs/Skill-Doctor/)

Score history