Vibe coders
You built a working product with AI and need a clear answer before putting it online.
Open-source defensive security skills for AI coding agents
Your AI can build it. Linmas helps you review it.
Linmas helps vibe coders, solo developers, and engineering teams check AI-assisted code for common security risks, understand why each finding matters, and apply concrete fixes before shipping. It works with Codex, Claude Code, and compatible AI coding agents.
Defensive use onlyConcrete remediationHuman review required
review this API change before I deploy- Risk
- High · SQL injection
- Impact
- An attacker may read or modify database records.
- Decision
- Fix before deploy
- Fix
- Use a parameterized query and validate input length.
- Verify
- Add a regression test, then re-run the review.
Security finding
You do not need to know security jargon first. Linmas explains the risk, the fix, and how to verify it.
v0.8.0current release
11security skills
7native MCP tools
3policy packs
Apache-2.0license
Codex-firstportable design
Built for people who can ship code, even if security is not their specialty yet.
Security may not be your first concern when you are learning to turn prompts into working products. Linmas adds a practical review checkpoint without needing a dedicated security team.
Match your role to a first review path.
Start with: Secure Code Reviewer
Solo developers
You move quickly but do not have an AppSec specialist reviewing every change.
Engineering teams
You need consistent findings, severity, remediation, and verification across projects.
Security practitioners
You want bounded, inspectable workflows that do not overclaim automated authority.
Working code can still be unsafe code.
AI makes it easier to build features quickly. It does not automatically add authorization checks, safe database queries, secret handling, or secure deployment configuration.
review.input / common failure modes4 signals
The page works, but anyone can access another user’s data
Linmas checks ownership and authorization boundaries.
IDORThe search feature works, but user input reaches raw SQL
Linmas identifies injection risk and shows a parameterized fix.
InjectionThe app deploys, but a token or secret is exposed
Linmas prioritizes secret leakage and sensitive logging before polish.
ExposureA scanner reports a warning, but you do not know what to do next
Linmas connects each finding to risk, remediation, and verification.
No actionWorking output is not approval. Review the boundary, apply the fix, and verify again.
A security review workflow you can understand and repeat.
Give your AI coding agent a clear scope, send it to the right Linmas skill, review the finding, then verify the fix. Automation helps the decision. It does not replace your judgment.
- scope / input
Choose a change
Review a named diff, file, endpoint, feature, or deployment plan.
target = diff | file | endpoint | feature | deployment plan - route / specialist
Use the right skill
Start with the router when you do not know which security domain applies.
route = linmas-security-domain-router - review / evidence
Get an actionable finding
See severity, risk, evidence, concrete remediation, and validation steps.
output = severity + risk + evidence + remediation + validation - fix / verify
Fix and verify
Apply the remediation, add a regression test, and re-run the review.
verify = fix + regression test + repeat review
Focused specialists instead of one oversized security prompt.
Start with the domain router when the risk is unclear. Use a specialist when you already know the type of review you need.
Build securely
Code, architecture, and cloud changes
linmas-secure-code-reviewer
Find code-level security risks and return concrete fixes plus regression checks.
Inspect skill ↗linmas-secure-systems-architect
Review trust boundaries, identity, control placement, abuse cases, and blast radius.
Inspect skill ↗linmas-cloud-hardening-architect
Harden IAM, workload identity, network boundaries, IaC, logging, and rollout safety.
Inspect skill ↗Operate securely
Production readiness, monitoring, and incidents
linmas-security-operations-lead
Build monitoring workflows, escalation paths, runbooks, and response readiness.
Inspect skill ↗linmas-detection-rules-engineer
Design SIEM logic, map telemetry, tune false positives, and validate alert behavior.
Inspect skill ↗linmas-incident-triage-lead
Classify incidents, preserve evidence, plan containment, recover safely, and communicate.
Inspect skill ↗Investigate and validate
Authorized defensive analysis
linmas-threat-research-analyst
Analyze indicators, adversary behavior, and defensive intelligence with clear confidence.
Inspect skill ↗linmas-exploit-validation-specialist
Safely validate owned or explicitly authorized systems with bounded proof of impact.
Inspect skill ↗linmas-smart-contract-reviewer
Review smart contracts, protocol assumptions, authorization, and economic security risks.
Inspect skill ↗Route and govern
Choose the right workflow and document controls
linmas-security-domain-router
Route unclear or multi-domain work to the best-fit specialist before context expands.
Inspect skill ↗linmas-controls-compliance-reviewer
Map controls, assess evidence, identify gaps, and prepare audit-readiness actions.
Inspect skill ↗Choose the path that fits what you want to do.
New to security? Start with the Secure Code Reviewer first. It is the simplest checkpoint for code created through a vibe coding workflow.
Check your setup
Confirm whether Codex or Claude Code is detected on your machine.
npx linmas detectInstall one focused skill
Start small with the Secure Code Reviewer instead of installing everything blindly.
Review one real change
Give the agent a named file, diff, endpoint, or feature and ask for remediation plus verification.
Recommended for beginners
Install one security skill
Add the Secure Code Reviewer to a detected Codex or Claude Code managed skill directory.
npx linmas install linmas-secure-code-reviewerRequires Node.js 24+. Use
npx linmas detect first when you are unsure which hosts are available.Try this after installation
Review the authentication and authorization changes in src/routes/users.js. Report severity, risk, concrete fixes, and how I should verify each fix. Do not modify files yet.
Codex primary path
Install the Codex plugin
Add the public GitHub marketplace and pin the current release.
codex plugin marketplace add TanKimGwan/linmas --ref v0.8.0Restart Codex completely and create a fresh task after installation.
No model call
Run the offline proof demo
Inspect the review pipeline without provider credentials or network model execution.
git clone https://github.com/TanKimGwan/linmas.git
cd linmas
npm install
npm run demo:judgeThe default demo replays a checked-in synthetic SQL-injection finding and validates the result in memory.
Keep evidence of what was reviewed, not just a chat response.
A Review Capsule is a versioned JSON record that ties one explicit input to the selected skill, normalized finding, policy decision, and the requirement for human review.
Exact input identityA SHA-256 digest and byte length connect the review to a concrete artifact.
Bounded metadataCredentials, raw provider responses, sessions, email addresses, and request identifiers are excluded.
Honest limitationA capsule is evidence of a review, not certification that software is secure.
review-capsule.jsonschema valid
{
"schemaVersion": "1.0",
"input": {
"sha256": "3f89…c21a",
"bytes": 1842
},
"review": {
"skill": "linmas-secure-code-reviewer",
"mode": "offline-fixture"
},
"finding": {
"severity": "high",
"category": "sql-injection"
},
"policy": {
"decision": "blocked"
},
"humanReviewRequired": true
}Native where verified. Portable where honest.
Linmas does not call every Markdown integration “native.” Host support requires deterministic detection, install and uninstall tests, safety-boundary parity, and a maintenance owner.
Primary / native
Codex
Git marketplace plugin, 11 managed skills, 7 native MCP tools, offline judge, and provider-backed review.
Verified compatible
Claude Code
Managed installation of 11 skills and Claude API provider-backed review.
Portable / manual
Other coding agents
Markdown instructions can be imported or adapted where equivalent skill support exists. Native integration is not implied.
Inspect the project, release process, and safety boundaries for yourself.
Trust should come from readable source code, repeatable validation, clear limitations, and a public contribution path. Not from marketing claims.
Snapshot verified against the Linmas main branch and npm metadata on.
Current release
Review the latest security, reliability, compatibility, and upgrade changes before updating.
View release notes ↗Canonical skills
The filesystem and validation command are the source of truth for inventory.
Inspect skills ↗Policy packs
Built-in packs are schema-validated and remain advisory, with human review required.
Inspect policies ↗Open-source license
Review the license and trademark boundaries before redistribution.
Read license ↗Vulnerability reporting
Report security issues through the project’s documented process.
Read policy ↗Public implementation record
Review the dated evidence, reproducibility commands, and known limitations.
Read record ↗linmas / latest notes
Latest Articles
Practical notes on defensive security, AI-assisted development, and repeatable review workflows.
Why AI-Generated Code Still Needs a Security Review
Working AI-assisted code can still cross authorization, data, and deployment boundaries. A small review loop makes those risks visible before shipping.
Read articleQuestions to answer before your first review.
Linmas is designed to lower the entry barrier, not hide its limitations. These answers describe what the project can and cannot do.
Do I need to understand application security first?
No. Start with a concrete file, diff, endpoint, or feature. Linmas should explain the risk, why it matters, the fix, and how to verify it. You still need to read the result and decide whether the evidence is sufficient.
Which skill should a vibe coder install first?
Start with linmas-secure-code-reviewer for code changes. Uselinmas-security-domain-router when you are unsure whether the problem belongs to code, cloud, architecture, incident response, or another security domain.
Does Linmas guarantee that my application is secure?
No. A review can miss context, logic flaws, deployment conditions, or new attack techniques. Linmas provides a first defensive checkpoint and structured evidence; it is not certification or automatic approval.
Does Linmas upload my code?
Offline commands do not call a model. Provider-backed reviews transmit the explicitly selected input only after the live execution path is enabled and confirmed. Review provider behavior, account configuration, and the documented safety boundary before sending sensitive code.
Is Linmas a hacking or exploitation tool?
No. Linmas is defensive and intended for owned or explicitly authorized systems. Its validation workflows emphasize bounded scope, evidence, remediation priority, and human review.
What should I do when a finding says “High” or “Blocked”?
Do not deploy the affected change yet. Confirm the evidence, apply the recommended remediation, add a regression test where possible, and repeat the review. Escalate to an experienced reviewer when the impact is unclear or affects authentication, authorization, secrets, payment, or sensitive data.
A first defensive checkpoint, not a final authority.
Linmas is designed to improve human security decisions without pretending that an AI response can certify software as secure.
What Linmas is designed to do
Provide focused, repeatable, inspectable defensive review workflows for authorized software work.
- Explain findings in practical developer language.
- Prioritize severity, risk, and remediation.
- Provide verification and regression steps.
- Keep human judgment visible and required.
What Linmas does not claim
Linmas does not replace accountable reviewers, guarantee complete isolation, or prove that software is secure.
- Not a certification or approval authority.
- Not an offensive exploitation platform.
- Not affiliated with any government institution.
- Not endorsed by OpenAI.
Before you deploy the product AI helped you build, give it one security review.
Start with the Secure Code Reviewer. You will get a prioritized finding, a concrete fix, and a verification step, without needing to become a security specialist first.