What problem does it solve? Reviewing code changes for security regressions is error-prone: small diffs can reintroduce vulnerabilities, removed validation checks go unnoticed, and reviewers lack a systematic way to assess blast radius and test coverage. This Skill provides a structured, evidence-based methodology for security-focused differential review. ## Core Features & Use Cases - Risk-Adaptive Analysis: Classifies changes by risk level (HIGH/MEDIUM/LOW) and adapts review depth to codebase size (SMALL/MEDIUM/LARGE) with DEEP, FOCUSED, or SURGICAL strategies. - Git History & Regression Detection: Uses git blame and commit history to detect removed security checks, re-added vulnerable code, and regressions of previous fixes. - Blast Radius & Test Coverage: Quantifies caller impact for modified functions and flags untested high-risk changes that should block merges. - Adversarial Modeling: Builds concrete attacker models and exploit scenarios for HIGH RISK changes, with structured vulnerability report templates. - Use Case: A team reviewing a PR that modifies an authentication module uses this Skill to triage changed files, git-blame removed validation, calculate blast radius, model exploit scenarios, and produce a comprehensive markdown report with severity ratings and recommendations. ## Quick Start Ask the AI to perform a differential security review of the current pull request or commit range and generate a markdown report with findings, blast radius, and recommendations.
