Back to directory

vbsec

A free security-scanning skill for Claude Code, Codex, and Antigravity that traces data flow through AI-written code to find and explain 21 common vulnerability types.

vbsec

vbsec is a security scanning skill that reads a codebase and looks for the most common vulnerabilities found in AI-generated code, such as hardcoded passwords, SQL injection, broken access control, JWTs accepted without signature verification, and overly permissive CORS. For each issue it explains why it is dangerous, how an attacker could exploit it step by step, shows the current code, and suggests a fix.

Instead of matching text patterns, it traces how data flows from user input to the dangerous call, which the project says produces far fewer false positives than pattern-based scanners. It analyzes five languages in depth, Go, PHP, TypeScript/JavaScript, Python, and .NET/C#, including popular frameworks such as Express, NestJS, Next.js, React, Django, FastAPI, Laravel, and ASP.NET Core, and can scan a whole repository, only uncommitted changes, a single commit or pull request, or a range of recent commits. On large repositories it splits the work across several agents running in parallel and merges the results, and it can produce reports in English or Vietnamese, including a JSON summary for CI/CD.

More in Code quality

See all 94
  • Critic

    critic.run

    A code-change viewer, backed by Y Combinator, built for reviewing work written by coding agents, presenting a plain-language narrative of each change alongside the diff and a running conversation with the agent.

  • GitIntel

    hoangsonww.github.io

    An MCP server that computes git repository analytics such as hotspots, churn, temporal coupling, knowledge maps and risk scoring entirely from local commit history, for AI coding agents like Claude Code and Codex.

  • Axint

    axint.ai

    A verification layer for AI coding agents working on Apple projects: it runs real Xcode builds and tests against the Swift an agent wrote, reconciles static analysis findings against that evidence, and returns a signed proof with the exact repairs still needed.