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 high-impact changes buried in large diffs. This Skill provides a structured, evidence-based workflow that catches security regressions before merge. ## 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), focusing effort where it matters. - Git History Forensics: Uses git blame and log searches to detect removed security checks, re-added vulnerable code, and regressions of previous CVE fixes. - Blast Radius & Adversarial Modeling: Quantifies how many callers each changed function affects and builds concrete attacker models with step-by-step exploit scenarios. - Use Case: A team reviews a PR that modifies a smart contract's withdraw function. The Skill detects a removed require(amount > 0) check, traces it back to a prior security fix commit, calculates 23 affected callers, and generates a markdown report with a CRITICAL finding and proof-of-concept exploit. ## Quick Start Ask the AI to perform a differential security review of the current pull request or commit range and generate a markdown report.
