← All skills

agent-runtime-validation

100 / 100 · Low risk

Fine to try.

By zero-lab-ai/skills (GitHub) · coding · 152 stars · scanned at commit 1e2f93f

Plans and evaluates bounded runtime tests of AI agents, tools, memory, hooks, approvals, and scope enforcement. Use when static review is complete and an authorized assessment must determine how the deployed agent actually behaves.

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/'agent-runtime-validation' ] || [ -L ~/.agents/skills/'agent-runtime-validation' ]; then echo 'A skill folder named agent-runtime-validation already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/zero-lab-ai/skills' "$d" && git -C "$d" checkout --quiet '1e2f93fed4c8fdb0d7fb35c72c3b0763d2d73cac' -- 'plugins/agent-security/skills/agent-runtime-validation' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/agent-security/skills/agent-runtime-validation' ~/.agents/skills/'agent-runtime-validation' && 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/'agent-runtime-validation' ~/.claude/skills/'agent-runtime-validation' (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 zero-lab-ai/skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/zero-lab-ai/skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/zero-lab-ai/skills/)

Score history