gstack-review

Analyze PR diffs for SQL safety and LLM trust boundary issues.

1|1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/tan-yong-sheng/GrowChat --skill gstack-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gstack-review
Source: https://github.com/tan-yong-sheng/GrowChat/tree/main/.claude/skills/gstack-review
Command: npx skills add https://github.com/tan-yong-sheng/GrowChat --skill gstack-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Pre-landing PR reviews to catch issues early by analyzing the diff for SQL safety, LLM trust boundary violations, and potential side effects.

Core Features & Use Cases

  • Analyzes SQL safety in diffs and flags potential injection risks.
  • Checks for LLM trust boundary violations and unintended prompt leakage.
  • Recommends remediation steps and best practices for pre-landing reviews.

Quick Start

Use the gstack-review command to run a pre-landing PR review on the targeted diff.

Frequently Asked Questions about gstack-review

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

FAQPage Schema
How do I check PR diffs for SQL injection risks before merging?

To check PR diffs for SQL injection risks, you can use pre-landing code review tools to analyze database queries and flag potential SQL safety issues. This process enforces safe patterns and provides concrete remediation suggestions before code is merged.

How do I detect LLM prompt leakage in code reviews?

Detecting LLM prompt leakage in code reviews involves analyzing diffs for trust boundary violations and unintended prompt exposure. Pre-landing review tools identify these risky side effects and recommend remediation steps to ensure safe LLM interactions.

What is a pre-landing PR review?

A pre-landing PR review is an early code analysis process that checks feature branch diffs for safety and trust issues before merging. It surfaces SQL injection risks and LLM boundary violations to enforce safe coding patterns early.

Does pre-landing code review work across base and feature branches?

Yes, pre-landing code review works across base and feature branches by analyzing the targeted diff. It evaluates changes touching database queries or LLM prompts to flag risky side effects and recommend best practices before merging.

What is the best way to automate risk analysis for LLM trust boundaries?

Automating risk analysis for LLM trust boundaries is best achieved by running pre-landing checks on PR diffs. This approach identifies unintended prompt leakage, enforces safe patterns, and generates concrete remediation suggestions for any flagged violations.