validate-security

Analyze git diffs for security violations and return a structured JSON report.

22|3|Updated Jan 30, 2026
One-click install
npx skills add https://github.com/peteski22/claude-pragma --skill validate-security
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: validate-security
Source: https://github.com/peteski22/claude-pragma/tree/main/skills/validators/security
Command: npx skills add https://github.com/peteski22/claude-pragma --skill validate-security

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automatically analyzes code changes to detect security vulnerabilities, helping teams prevent insecure code from entering the main branch.

Core Features & Use Cases

  • Hard violations detection: Secrets, credentials, injection flaws, path traversal, insecure configurations, and authentication/authorization gaps.
  • Should violations guidance: Identifies insecure configurations and enforcement gaps, with actionable remediation hints.
  • Diff-based analysis & batching: Scans git diffs and staged changes, supporting batched processing (up to 50 files per run) for scalable validation.
  • Auditable reporting: Outputs a structured JSON report detailing violations, affected files, and pass/fail status to guide fixes during code review.

Quick Start

Run the security validator against the current diff by invoking the /validate command in your project context. It will return a JSON report with hard/should/warn violations and a summary to guide fixes.

Frequently Asked Questions about validate-security

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I scan git diffs for security vulnerabilities before committing code?

To scan git diffs for security vulnerabilities, invoke the /validate command against staged or unstaged changes. The validator analyzes the code diff and returns a structured JSON report detailing any detected vulnerabilities.

What types of security issues can static analysis detect in code changes?

Static analysis of code changes detects secrets, credentials, injection flaws, path traversal, insecure configurations, and authentication gaps. It categorizes these findings into hard, should, and warn violations to guide remediation.

Does the security validator support batched processing for large codebases?

Yes, the security validator supports batched processing for large codebases by batching up to 50 files per run. This allows scalable validation of staged files and git diffs without overwhelming the analysis process.

Can I use this to catch hardcoded secrets and credentials in staged files?

Yes, you can catch hardcoded secrets and credentials in staged files. The validator operates on staged and unstaged git diffs, flagging them as hard violations in the structured JSON report to prevent insecure code from shipping.

How do I get an auditable report of security violations found in my code?

To get an auditable report of security violations, run the validator on your git diff. It outputs a structured JSON report containing the pass or fail verdict, detailed violations, and affected files to guide fixes during code review.

What is the file limit for analyzing code changes with static analysis?

The file limit for analyzing code changes is 50 files per run. The validator reads git diffs from HEAD~1, staged, or unstaged states and batches processing to handle this volume efficiently.