AISecurity
Security audits, code review, and test-driven development checks
All Skills in This Repository (5)
Pure Emerald Level Indicators
DmitrL-devsentinel-ai-security
Detect and block AI threats in prompts and responses across LLM workflows.
DmitrL-devAgent Security Audit
Identify AI agent security weaknesses using the OWASP Agentic Top 10 2026 framework.
DmitrL-devTDD Enforcement
Enforce a failing test before production code in software projects.
DmitrL-devQA Fix Loop
Coordinate Reviewer and Fixer agents to detect issues, apply fixes, and re-review.
DmitrL-devTwo-Stage Code Review
Separate spec compliance and code quality reviews into two stages.
Frequently Asked Questions
FAQPage SchemaHow to install AISecurity?▼
Run `npx skills add DmitrL-dev/AISecurity --all -g -y` in your terminal to install all skills in this suite globally.
How to audit an AI agent for security risks?▼
The Agent Security Audit skill checks your codebase against the OWASP Agentic Top 10, flagging issues like prompt injection, uncontrolled tool execution, and missing rate limits with severity ratings and fixes.
What is the QA Fix Loop skill?▼
It runs an autonomous cycle where a reviewer finds issues and a fixer corrects them, repeating until the code passes or escalating to a human after three iterations.
How does two-stage code review work?▼
It splits review into two passes: first checking the code meets the specification, then checking code quality, so neither type of problem gets overlooked.
Does AISecurity enforce test-driven development?▼
Yes. The TDD Enforcement skill applies the rule that no production code is written without a failing test first, following the red-green-refactor cycle.
Related Repositories in Software Engineering
View All in Software Engineering→
openclawopenclaw
Run a personal AI assistant across your devices and chat apps
obrasuperpowers
Gives coding agents a disciplined workflow from idea to merged code
facebookreact
AI agent skills for building, testing, and porting React core