Updated today
by avivgerz-hue
vibe-shield
60-rule static security scanner, MCP server & skill poisoning auditor for AI-generated codebases (Claude Code, Codex, Cursor).
21 GitHub stars (21)
+21 in 2 days
- 2 skills (2 skills found in its SKILL.md files)
- 2 forks (2 forks)
- Today last update (Last updated today)
Install
Skills CLI
npx skills add avivgerz-hue/vibe-shield
Asks which skills and agents to install. Just one: npx skills add avivgerz-hue/vibe-shield --skill vibe-shield — add -g for every project.
Claude Code
git clone https://github.com/avivgerz-hue/vibe-shieldcp -r "vibe-shield" ~/.claude/skills/vibe-shield
Copies the vibe-shield skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add avivgerz-hue/vibe-shield
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.
-
vibe-shield
Apply a six-phase defensive security review to changes affecting applications, APIs, data, AI agents, and MCP configuration. Use static evidence, preserve behavior, and report limitations.
SKILL.md on GitHub (opens in a new tab) -
deploy
Deploy the app and report status
tests/fixtures/ on GitHub (opens in a new tab)vulnerable/ .claude/ skills/ deploy/ SKILL.md
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.