vibe-security
Skill1 starsChanged 5 months agoMITView on GitHub
Audit a vibe-starter app against the security checklist and report findings. Use when the user wants a security review or audit, asks whether the app is safe to ship, or runs /vibe-security.
- Reads credentials
2 other projects use a version of this.
Adopted by
Most recently taken up by
- toby7979/sealmyapp-toolstheir own version, first seen Oct 17, 2026
- raroque/vibe-security-skilltheir own version, first seen Mar 15, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- raroque/vibe-security-skill★ 996same name
- toby7979/sealmyapp-tools★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- vibe-buildSkill
- vibe-legalSkill
- vibe-starterSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Before shipping, after a batch of /vibe-build changes, or whenever the user wants assurance.
- Distinctive: line 41
Read server actions and route handlers.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
vibe-security
Audit the current app and report concrete findings, most severe first. This is a read-and-check skill: it inspects, it does not silently change code. Offer fixes after reporting.
When to use
Before shipping, after a batch of /vibe-build changes, or whenever the user wants assurance.
How to run the audit
Work through references/audit.md. Gather evidence with the tools below, then judge each item.
Headers and CSP
Build and start the app, then inspect the response:
curl -sI http://localhost:3105/ | grep -iE "content-security-policy|strict-transport|x-frame|x-content-type|referrer-policy|permissions-policy"Confirm every header is present, and that the production script-src uses a nonce with
strict-dynamic and has no unsafe-inline or unsafe-eval.
Secret exposure
grep -rnE "process\.env\.[A-Z_]+" app components lib | grep -v "NEXT_PUBLIC_"Flag any server secret referenced inside a file marked "use client". Confirm .env.local is
gitignored and only .env.example is committed.
Input and mutations
Read server actions and route handlers. Flag any that accept input without a Zod parse, any mutation on a GET, and any database call built with string concatenation.
Authorization
Flag any protected route, action, or admin surface that does not check the session and ownership.
Dependencies and secrets in history
pnpm audit --prod
gitleaks detect --no-banner 2>/dev/null || echo "install gitleaks for history scanning"Accessibility
pnpm run lintConfirm the jsx-a11y rules pass and interactive elements have accessible names.
Reporting
Produce a short report: each finding with a severity (high / medium / low), the file and line,
what is wrong, and the fix. End with a one-line verdict on whether it is safe to ship. If the user
approves, apply the fixes following the vibe-build conventions.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

