security

Review code changes for security vulnerabilities and trust-boundary failures.

20|4|Updated May 14, 2026
One-click install
npx skills add https://github.com/crewrig/crewrig --skill security-crewrig
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: security
Source: https://github.com/crewrig/crewrig/tree/main/artifacts/core/skills/security
Command: npx skills add https://github.com/crewrig/crewrig --skill security-crewrig

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you review code changes through a security lens so you can spot realistic exploit paths, secret leaks, and dependency risks before they reach production.

Core Features & Use Cases

  • Threat-focused code review: Traces trust boundaries and identifies how untrusted input could reach dangerous sinks.
  • Security-sensitive change review: Useful for authentication, authorization, secrets, cryptography, parsing, deserialization, network calls, and dependency upgrades.
  • Evidence-based findings: Prompts you to verify issues end-to-end and report concrete evidence, severity, and fixes instead of vague speculation.
  • Use case: Review a pull request that adds a new API integration or changes login handling and produce a concise list of actionable security findings.

Quick Start

Ask the security skill to review the change for realistic vulnerabilities, trace the data flow, and report any confirmed findings with severity, evidence, and a fix.

Frequently Asked Questions about security

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

FAQPage Schema
How do I review code changes for security vulnerabilities before merging?

Code review for security vulnerabilities involves tracing trust boundaries to identify how untrusted input reaches dangerous sinks. This Skill evaluates authentication, cryptography, and parsing changes to provide evidence-based confirmation of exploit paths and severity.

What is threat modeling in the context of a pull request review?

Threat modeling during a pull request review maps untrusted data flow across trust boundaries to find realistic exploit paths. It focuses on security-sensitive areas like authorization and deserialization, requiring concrete evidence and remediation steps rather than speculation.

Can I audit dependency upgrades for potential vulnerability risks?

Yes, you can audit dependency upgrades for vulnerability risks. This Skill reviews dependency changes to identify potential security issues, requiring evidence-based verification of data flow and exploit path to report concrete severity and fixes.

How do I verify if an outbound network call introduces a security risk?

To verify if an outbound network call introduces a security risk, trace the data flow from untrusted inputs to the network sink. This Skill helps identify trust-boundary failures and requires concrete evidence of the exploit path and severity before reporting.

Does this approach work for reviewing secret hygiene in code changes?

Yes, this approach works for reviewing secret hygiene in code changes. It evaluates how secrets and cryptography are handled across trust boundaries, verifying data flow and exploit paths to produce actionable findings with concrete remediation steps.