← All skills

llm-security

80 / 100 · Low risk

Fine to try.

By coco-research/coco (GitHub) · coding · 630 stars · scanned at commit cd89f01

Use for authorized security assessment of LLM applications and AI agents, including prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'llm-security' ] || [ -L ~/.agents/skills/'llm-security' ]; then echo 'A skill folder named llm-security already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/coco-research/coco' "$d" && git -C "$d" checkout --quiet 'cd89f013b617f7eea982a9bbc60e992974fda2aa' -- 'systems/reverse-skill/skills/llm-security' && mkdir -p ~/.agents/skills && cp -R "$d"/'systems/reverse-skill/skills/llm-security' ~/.agents/skills/'llm-security' && 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/'llm-security' ~/.claude/skills/'llm-security' (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 coco-research/coco shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/coco-research/coco.svg)](https://zalavijaysinh.github.io/skilltrust/repos/coco-research/coco/)

Score history