Security & Testing Agent Skills for OpenAI Agents SDK

This skill should be used when the user asks to "attack Active Directory", "exploit AD", "Kerberoasting", "DCSync", "pass-the-hash"…

This skill should be used when the user asks to "learn ethical hacking", "understand penetration testing lifecycle", "perform…

This skill should be used when the user asks to "test for HTML injection", "inject HTML into web pages", "perform HTML injection attacks"…

This skill should be used when the user asks to "automate SQL injection testing," "enumerate database structure," "extract database…

This skill should be used when the user asks to "identify web application vulnerabilities", "explain common security flaws", "understand…

Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with…

Reference skill for Zoom Probe SDK. Use after routing to a preflight workflow when testing browser compatibility, media permissions, audio…

Ensure latest version of Cassandra is installed

Ensure that all Namespaces have Network Policies defined (Automated)

Comprehensive web accessibility (a11y) audit and compliance skill.

Route a free-text agent-skill security finding to the one OWASP AST01-AST10 category that owns its root cause, separate that origin from…

Open security scanner for agentic infrastructure — agents, MCP, packages, blast radius, runtime, and trust across MCP discovery, CVEs…

On-chain identity for OpenClaw agents — .null name, ETH↔Solana binding, verifiable agent identity without touching private keys

Enforces deterministic code-level safety boundaries, idempotency, human-in-the-loop approvals, and concurrency isolation in AI agent…

Local pre-action trust boundary for agents before installing skills, enabling tools/MCP servers, exposing secrets, or approving risky…

GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously.

Local-evidence production readiness audit for shipped apps, pre-launch reviews, post-merge checks, and "what breaks in prod?" questions…

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing…

Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using…

A comprehensive verification system for Claude Code sessions.

Use when setting up a secure email inbox for any AI agent — configuring inbound email via Resend, webhooks, tunneling for local…