secure

Scan codebases for secrets, dependencies, and OWASP threats.

2|1|Updated Apr 13, 2026
One-click install
npx skills add https://github.com/Epiphytic/brains --skill secure-epiphytic
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: secure
Source: https://github.com/Epiphytic/brains/tree/main/skills/secure
Command: npx skills add https://github.com/Epiphytic/brains --skill secure-epiphytic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Secure provides a structured, repeatable process to find and remediate security issues in a codebase, including secrets, dependency vulnerabilities, insecure configurations, and design-level threats, reducing the risk of production compromise.

Core Features & Use Cases

  • Secrets Scanning: Detects hardcoded keys, .env leaks, and suspicious encodings across common source files.
  • Dependency Audit: Runs or guides audits for npm, pip, Cargo, and Go dependencies and surfaces known CVEs.
  • OWASP & Threat Modeling: Checks code and architecture against OWASP Top 10 categories and produces STRIDE-based threat models.
  • Multi-LLM Review Modes: Supports single-LM local scans, council-style parallel reviews, and debate-style multi-round deliberation for high-confidence findings.
  • Remediation Workflow: Prioritizes findings, writes a committed security report in docs/plans/, and files follow-up beads tasks when scoped to plan phases.

Quick Start

Run the secure skill to scan the repository for secrets, perform dependency and OWASP checks, generate a prioritized security report, and propose or commit remediation changes.

Frequently Asked Questions about secure

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I scan my codebase for hardcoded secrets and dependency vulnerabilities?▼

To scan your codebase for hardcoded secrets and dependency vulnerabilities, you can run a comprehensive security review that detects leaked keys, runs npm or pip audits for known CVEs, and generates a prioritized remediation report.

What is the best way to perform an OWASP Top 10 assessment on source code?▼

The best way to perform an OWASP Top 10 assessment is to check your source code and architecture against standard vulnerability categories, generate STRIDE-based threat models, and produce a committed security report under your docs directory.

Can I use multi-LLM review modes for high-confidence threat modeling?▼

Yes, you can use multi-LLM review modes for high-confidence threat modeling by configuring council-style parallel reviews or debate-style multi-round deliberation alongside standard local scans to validate security findings.

How do I audit npm, pip, Cargo, and Go dependencies for known CVEs?▼

To audit npm, pip, Cargo, and Go dependencies for known CVEs, run a dependency audit workflow that surfaces vulnerable packages across your project ecosystems and prioritizes them in a structured remediation plan.

Does threat modeling work with recent git diffs or does it require the full repository?▼

Threat modeling and secrets scanning work with both recent git diffs and the full source repository, allowing you to target specific code changes or perform a comprehensive standalone security review of the entire codebase.