What problem does it solve? Go codebases often ship with preventable vulnerabilities like SQL injection, weak cryptography, hardcoded secrets, and missing security headers. This Skill gives an AI agent a structured security methodology — threat modeling, severity scoring, and domain-specific checklists — to review, audit, or write Go code that resists common attack patterns. ## Core Features & Use Cases - Three operating modes: Review mode for PR security analysis, Audit mode that launches parallel sub-agents across five vulnerability domains with DREAD scoring, and Coding mode for writing secure new code. - Comprehensive vulnerability references: Detailed guides covering injection (SQL, command, XSS, SSRF), cryptography (AES-GCM, Argon2id, TLS), filesystem safety (path traversal, ZipSlip), cookies, secrets management, logging, and security architecture patterns. - Tooling integration: Configures gosec, govulncheck, race detector, and fuzz testing for automated verification. - Use Case: Before merging a PR that adds a file-upload endpoint, run an audit to catch path traversal risks, missing request body limits, and insecure file permissions — each finding scored by severity with a concrete fix. ## Quick Start Ask the agent to audit your Go project for security vulnerabilities and report findings ranked by DREAD severity.