Krigsexe

Krigsexe / ai-rsk

Public

Security gate for AI-generated code - blocks the build until vulnerabilities are fixed

airsk.organicascode.me agentic-coding ai ai-coding anthropic claude-code
11
2
100% credibility
Found Mar 17, 2026 at 11 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Rust
AI Summary

ai-rsk is a security tool that scans AI-generated code for vulnerabilities, enforces fixes before builds, and integrates compliance checks for privacy, accessibility, and more.

How It Works

1
🔍 Discover safe AI coding

You hear about a simple tool that checks AI-written code to catch security mistakes before they cause problems.

2
📥 Get the program

Download the ready-to-use program that fits any coding project, no complicated setup needed.

3
⚙️ Set it up once

Put it in your project folder and run a quick setup to choose safety checks like privacy rules or accessibility.

4
🛡️ Scan your code

Run the check and see a clear list of issues with easy fixes, so your AI code gets safer instantly.

5
✏️ Fix with guidance

Follow the simple instructions or let your AI helper make the changes until everything passes.

✅ Build securely

Your project builds perfectly, protected from common pitfalls, ready to share with confidence.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 11 to 11 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is ai-rsk?

ai-rsk is a Rust-built security gateway that scans AI-generated code for vulnerabilities, blocking builds until fixes land. It catches LLM pitfalls like tokens in localStorage, missing security headers, and prompt injection via 55 regex rules, plus semgrep, gitleaks, and osv-scanner for deeper checks. Run `ai-rsk scan --full` in prebuild hooks or GitHub Actions to enforce security, GDPR, AI Act, SEO, and accessibility profiles.

Why is it gaining traction?

Unlike generic scanners, ai-rsk targets AI-specific flaws that slip past github security scanning or copilot suggestions, like client-side auth or CORS wildcards. It auto-installs tools, generates git hooks and LLM discipline files for tools like Cursor or Claude, and fails builds with exit code 1—forcing AIs to iterate fixes. Integrates seamlessly as a security github actions step or npm prebuild.

Who should use this?

Devs relying on github copilot or Claude for JS/TS apps, especially non-engineers prototyping with AI rsk. Teams building security gateway auto workflows in GitHub projects, or enforcing compliance in AI-heavy stacks like Next.js backends with Stripe webhooks.

Verdict

Early alpha with 11 stars and 1.0% credibility—test in side projects, not prod pipelines yet. Strong README and MIT license make it a low-risk watch for AI code security gateway needs; contribute rules to mature it fast.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.