What problem does it solve? Manual security code reviews often produce noisy, low-confidence findings or miss real vulnerabilities because reviewers lack systematic coverage of OWASP vulnerability classes and framework-specific mitigations. ## Core Features & Use Cases - Confidence-Based Reporting: Reports only HIGH confidence findings where attacker-controlled input is confirmed, filtering out false positives from framework auto-escaping, ORM parameterization, and server-controlled configuration values. - Comprehensive Vulnerability Coverage: Includes reference guides for injection, XSS, CSRF, SSRF, deserialization, authentication, authorization, cryptography, business logic, and supply chain risks, plus language guides for Python, JavaScript, Go, Rust, and Java, and infrastructure guides for Docker, Kubernetes, Terraform, CI/CD, and cloud. - Use Case: Ask for a security review of a new API endpoint diff; the skill traces data flow across the codebase, checks framework protections, and returns a structured report with severity, evidence, and remediation for each confirmed vulnerability. ## Quick Start Ask the AI to perform a security review of the current file or diff and report only high-confidence exploitable vulnerabilities with severity and fixes.
