What problem does it solve? Reviewing pull requests and commits for security regressions is error-prone: reviewers miss removed validation checks, re-introduced vulnerabilities, and untested high-risk changes, especially in large codebases. ## 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) using DEEP, FOCUSED, or SURGICAL strategies. - Git History & Blast Radius: Uses git blame and log searches to detect security regressions, calculates caller counts to quantify blast radius, and checks test coverage gaps. - Adversarial Modeling & Reporting: Builds concrete attacker models and exploit scenarios for HIGH RISK changes, then generates a comprehensive markdown report with severity tables, findings, and recommendations. - Use Case: A team merging an auth system rewrite across 450 files uses this Skill to baseline the original code, deep-analyze only the auth changes, model exploit scenarios, and produce a blocking/conditional merge recommendation report. ## Quick Start Ask the AI to perform a differential security review of the current pull request or commit range and generate a full markdown report.
