Updated 1mo ago
by T-Zevin
SkillGuardrail
Pre-install security scanner and guarded installer for Agent Skills. Quarantine, scan, enforce policy, and verify skills before they reach Codex, Claude Code, Cursor, Gemini CLI, or OpenClaw.
57 GitHub stars (57)
Steady at 57 stars — no new stars in the 16 days since Sep 30.
- 2 skills (2 skills found in its SKILL.md files)
- 13 forks (13 forks)
- 1mo ago last update (Last updated 1mo ago)
Install
Skills CLI
npx skills add T-Zevin/SkillGuardrail
Asks which skills and agents to install. Just one: npx skills add T-Zevin/SkillGuardrail --skill malicious-fixture — add -g for every project.
Claude Code
git clone https://github.com/T-Zevin/SkillGuardrailcp -r "SkillGuardrail/testdata/malicious-skill" ~/.claude/skills/
Copies the malicious-fixture skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add T-Zevin/SkillGuardrail
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
malicious-fixture
Deliberately unsafe fixture used only by SkillGuardrail tests.
testdata/malicious-skill/SKILL.md on GitHub (opens in a new tab) -
safe-summary
Summarize a local text file without network access.
testdata/safe-skill/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.