Back to browse
GitHub Repository

Static analysis for TypeScript / JavaScript LLM-application code. OWASP LLM Top 10 at commit time. A complement to Semgrep's p/ai-best-practices for the TS/JS ecosystem.

3 starsJavaScript

LLM-Audit – Semgrep Rules for OWASP LLM Top in TypeScript

by Javierlozo·Apr 29, 2026·1 point·0 comments

AI Analysis

●●SolidNiche Gem

Fills the TypeScript gap that Semgrep's official AI best practices pack misses.

Strengths
  • Targets specific AI failure modes like unvalidated JSON parsing of model output.
  • Outputs SARIF format for direct integration with GitHub Code Scanning pipelines.
  • Includes a 'doctor' command to diagnose missing dependencies before scanning.
Weaknesses
  • Only five rules implemented so far; needs more coverage to be production-ready.
  • Requires users to install Semgrep separately, adding friction to the onboarding flow.
Category
Target Audience

TypeScript developers building LLM applications

Similar To

Semgrep · Snyk Code · CodeQL

Similar Projects

Security●●Solid

LLM AuthZ Audit – find auth gaps and prompt injection in LLM apps

Purpose-built LLM security linter covers OWASP Top 10, but static analysis has inherent blind spots.

Big BrainSolve My Problem
iamspathan
104mo ago