Security & Testing Agent Skills for OpenAI Agents SDK

Guide secure migration of code from memory-unsafe languages (C, C++, Assembly) to memory-safe languages (Rust, Go, Java, C#, Swift).

Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development.

Design and implement automated tests for current Minecraft 26.x or legacy 1.21.x mods and plugins using JUnit, MockBukkit, NeoForge Game…

Hunting skill for csrf vulnerabilities. Built from 15 public bug bounty reports including modern variants — SameSite=Lax sibling-subdomain…

Review a repository, architecture, workflow, or local folder with a focus on MITRE ATT&CK-style adversary behavior.

Enforce and detect server-side the authorization and workflow rules a mobile client cannot be trusted to keep.

Add binary protections and, above all, remove client-side trust against OWASP Mobile Top 10 M7.

Abuse insecure deep links and inter-app entry points during an authorized mobile assessment.

Harden a mobile app's deep links and inter-app entry points so a crafted link cannot trigger sensitive actions, redirect callbacks, or…

Extract hardcoded secrets from a mobile app binary during an authorized mobile assessment.

Intercept and read a mobile app's network traffic during an authorized mobile assessment.

Secure a mobile app's supply chain against OWASP Mobile Top 10 M2.

Demonstrate Inadequate Supply Chain Security (OWASP Mobile Top 10 M2) during an authorized mobile assessment — showing that a mobile app…

Harden a mobile app's network transport so an adversary-in-the-middle on a hostile network cannot read or tamper with its traffic.

Generate mock data and test fixtures from schemas

You are an expert Rails model test developer.

REQUIRED and PRIMARY testing approach for packages/playground and packages/playground-ui.

Protect production environment files while allowing safe access to dev and QA configurations.

Run the Gauntlet Loop: analyze, plan, build, independently critique/red-team/verify, revise, re-verify, and judge until PASS, FAIL, or the…

Review multi-tenant AI deployments for cross-tenant context leakage, LoRA adapter contamination, shared inference worker risks, system…

This is a multiline description. It spans multiple lines. And should be normalized.