← All skills

authorization-model

100 / 100 · Low risk

Fine to try.

By wso2/labs-agentic-engineer (GitHub) · security · 24 stars · scanned at commit e3b5fc8

Read before deciding who may call what in a generated app — authoring or reviewing security.json, an openapi.yaml security block, a screen gate, a 401 handler, or a /me/ path. States the platform's authorization invariants once, with the reason each was measured.

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/'authorization-model' ] || [ -L ~/.agents/skills/'authorization-model' ]; then echo 'A skill folder named authorization-model already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/wso2/labs-agentic-engineer' "$d" && git -C "$d" checkout --quiet 'e3b5fc8668f26761380b2d4965719f2d8f2eb246' -- 'skills/authorization-model' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/authorization-model' ~/.agents/skills/'authorization-model' && 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/'authorization-model' ~/.claude/skills/'authorization-model' (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 wso2/labs-agentic-engineer shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/wso2/labs-agentic-engineer.svg)](https://zalavijaysinh.github.io/skilltrust/repos/wso2/labs-agentic-engineer/)

Score history