What problem does it solve? Go codebases often ship with preventable vulnerabilities like SQL injection, weak cryptography, path traversal, and leaked secrets. This Skill gives an AI coding agent a structured security methodology to review, audit, and write Go code that resists these attack classes. ## Core Features & Use Cases - Three operating modes: Review mode for PR security checks, Audit mode that fans out five parallel sub-agents across vulnerability domains (injection, crypto, web, auth, concurrency) with DREAD severity scoring, and Coding mode for writing secure new code. - Deep reference library: Detailed guides with bad/good Go code examples covering cryptography, injection, filesystem safety, cookies, logging, secrets management, threat modeling (STRIDE/DREAD), and security architecture patterns like Zero Trust and mTLS. - Tooling integration: Guidance for gosec, govulncheck, race detector, and fuzz testing to verify findings. - Use Case: Ask the agent to audit a Go microservice before release; it scans for hardcoded credentials, unsafe SQL concatenation, missing TLS configuration, and race conditions, then reports findings ranked by severity with concrete fixes. ## Quick Start Ask the agent to perform a security audit of your Go project using the golang-security skill and report findings by severity.