What problem does it solve? Security reviews are often skipped or done inconsistently before releases, leaving vulnerabilities like SQL injection, hardcoded secrets, and broken access control undetected until they become incidents. ## Core Features & Use Cases - Structured Security Audit: Runs a systematic STRIDE threat analysis plus OWASP Top 10 mapping across a scoped set of files, producing a severity-ranked findings report. - Secret and Dependency Scanning: Detects hardcoded API keys, tokens, and private keys via regex patterns, and runs stack-appropriate dependency audits (pnpm audit, pip-audit, govulncheck, cargo audit). - Iterative Auto-Fix Mode: With the --fix flag, applies one targeted fix per finding, verifies with a test/lint guard, commits each fix, and stops on regression. - Use Case: Before a release, run a full audit on your API layer to catch injection flaws and missing rate limits, then auto-remediate Critical and High findings with bounded iterations. ## Quick Start Ask the AI to run a security audit on your source directory, for example: audit src/api for security vulnerabilities and fix the critical findings with at most 10 iterations.