copilot-security-instructions

Analyze repository-grounded identity, access control, and authorization design with evidence-first reporting and script-validated Mermaid diagrams.

Triage a dependency CVE using local repo evidence and remediation guidance.

Threat model a system, feature, service, or PR using Shostack's 4Q workflow, evidence-first analysis, risk scoring, and CLI-friendly Mermaid helper scripts.

Analyze repository-grounded identity, access control, and authorization design with evidence-first reporting and script-validated Mermaid diagrams.

Threat model a system, feature, service, or PR using Shostack's 4Q workflow, evidence-first analysis, risk scoring, and CLI-friendly Mermaid helper scripts.

Review workflow for AI/LLM output usage to prevent over-trust, injection, and unsafe automation.

Process for tightening input validation, canonicalization, and safe parsing to prevent injection and logic abuse.

Workflow for preventing secret leaks and sensitive logging (PII/credentials) and adding redaction defaults.

Repeatable process for an application security code review that produces prioritized findings and fix guidance.

Standard validation checklist to prove a security fix works and doesn’t regress behavior.

Use this skill when creating or editing GitHub Copilot customization Markdown files (agent profiles, prompt files, instruction files, and skills).