← All skills

prompt-injection-review

100 / 100 · Low risk

Fine to try.

By Goldziher/ai-rulez (GitHub) · coding · 169 stars · scanned at commit 5cf1280

How to review code for prompt-injection risks. Load when reviewing an integration that sends user or repository text to a language model.

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/'prompt-injection-review' ] || [ -L ~/.agents/skills/'prompt-injection-review' ]; then echo 'A skill folder named prompt-injection-review already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Goldziher/ai-rulez' "$d" && git -C "$d" checkout --quiet '5cf12807a83f76882552503a51b1108bde33f257' -- 'tests/review/golden/skill-quality/fixtures/cases/injection-benign-security/prompt-injection-review' && mkdir -p ~/.agents/skills && cp -R "$d"/'tests/review/golden/skill-quality/fixtures/cases/injection-benign-security/prompt-injection-review' ~/.agents/skills/'prompt-injection-review' && 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/'prompt-injection-review' ~/.claude/skills/'prompt-injection-review' (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 Goldziher/ai-rulez shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/Goldziher/ai-rulez.svg)](https://zalavijaysinh.github.io/skilltrust/repos/Goldziher/ai-rulez/)

Score history