ai mitts
Browse Skills Tools GitHub

Tag: adversarial-testing

Type: All Skills Tools
Tags: mcp automation llm cli code-review unity typescript genomics game-development bioinformatics debugging documentation cloudbase ai-agents agentic-workflow devops llm-agent workflow-automation encode code-analysis
skill ★ 113

Adversarial code and security flaw critique

Initiates an adversarial council process where multiple agents collaboratively analyze provided code or answers to identify bugs, security vulnerabilities, and logical flaws. This mode is designed for deep, critical review of complex system…

agentic-box/owlex code-critique security-review bug-finding adversarial-testing
skill ★ 21,403

Redteam Plugin and Grader Development Standards

Provides standardised protocols for developing redteam plugins and graders, including XML tag requirements, rubric structures, and attack template configurations.

promptfoo/promptfoo red-teaming plugin-development promptfoo llm-evaluation
skill ★ 11

End-to-End Release Validation and QA

This skill performs comprehensive, adversarial end-to-end testing on a candidate release, deploying it in an isolated environment to validate all critical paths. It systematically checks the UI, API, security headers, and boundary condition…

Destrayon/Connapse e2e-testing security-audit api-validation adversarial-testing
Page 1
ai mitts

Agentic skills & tools, vector-searched.

Browse

All Skills Tools

About

Auto-discovered from public GitHub. Summarised by Ollama. Searched with nomic-embed-text.

© 2026 aimitts.