What problem does it solve? Security regressions and vulnerabilities often slip through code review because reviewers lack historical context, miss transitive callers, or underestimate small changes. This Skill systematically analyzes PRs, commits, and diffs to detect security regressions, missing validation, and access control bypasses before merge. ## Core Features & Use Cases - Risk-Adaptive Analysis: Classifies changes by risk level (HIGH/MEDIUM/LOW) and scales review depth to codebase size (SMALL/MEDIUM/LARGE). - Git History & Blast Radius: Uses git blame to detect regressions of previous security fixes and quantifies caller impact for prioritization. - Adversarial Modeling & Reporting: Builds concrete exploit scenarios with exploitability ratings and generates comprehensive markdown reports with severity tables and recommendations. - Use Case: Reviewing a smart contract PR that removes a require check, the Skill traces the check's origin via git blame, finds it was added for a CVE fix, models an exploit scenario, and flags it as a CRITICAL regression in the report. ## Quick Start Ask the AI to perform a differential security review of the current PR or commit range and generate a full markdown report.
