← All skills

tool-abuse-detection

97 / 100 · Low risk

Fine to try. Some of what it can do is expected: a security skill usually runs scanners and checks websites.

By Tencent/AI-Infra-Guard (GitHub) · security · 7,468 stars · scanned at commit 29e589c

Detect tool misuse and unexpected code execution via dialogue testing. Use when the agent exposes file, code-execution, or network tools.

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/'tool-abuse-detection' ] || [ -L ~/.agents/skills/'tool-abuse-detection' ]; then echo 'A skill folder named tool-abuse-detection already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Tencent/AI-Infra-Guard' "$d" && git -C "$d" checkout --quiet '29e589c88471a0fff732d8c38004ff2487be461c' -- 'agent-scan/agent_scan/prompt/skills/tool-abuse-detection' && mkdir -p ~/.agents/skills && cp -R "$d"/'agent-scan/agent_scan/prompt/skills/tool-abuse-detection' ~/.agents/skills/'tool-abuse-detection' && 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/'tool-abuse-detection' ~/.claude/skills/'tool-abuse-detection' (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 Tencent/AI-Infra-Guard shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/Tencent/AI-Infra-Guard.svg)](https://zalavijaysinh.github.io/skilltrust/repos/Tencent/AI-Infra-Guard/)

Score history