Security & Testing Agent Skills for Claude Desktop

Harden a LangChain 1.0 chain or LangGraph agent against prompt injection,\

Language-specific verification for Python, TypeScript/JavaScript, and Go.

Laravel 13 testing with Pest PHP 4 or PHPUnit 12.

OWASP Top 10 security audit and secure coding guidelines for Laravel + React/Inertia.js applications.

Security auditor for Laravel applications.

Laravel security best practices — authentication, authorization, Eloquent safety, CSRF, XSS prevention, API security, and secure…

Use when configuring Laravel-specific auth/session/CSRF/authorization plumbing - Sanctum SPA authentication, session cookie hardening…

Automate Lastpass tasks via Rube MCP (Composio).

This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create…

Sets up and runs libFuzzer, the coverage-guided fuzzer built into LLVM, on C/C++ code that compiles with Clang.

Use when a bounded system or design change needs a quick evidence-backed security analysis before implementation, approval, or release.

Configure enterprise role-based access control for Lindy AI workspaces.

Implement security best practices for Lindy agents and integrations.

Secure API key management, OAuth best practices, and webhook

Audits a repository against the Adversis v0 security baseline for agentic SaaS applications.

Sign Linux packages with GPG keys for secure distribution

Use for Livewire security work. Covers what a public property publishes, snapshot serialization, #[Locked], the persistent middleware gap…

Use when evaluating, ranking, monitoring, or selecting LLM/agent outputs or trajectories with explicit criteria, especially when…

Elicit confident, ungrounded fabrications from an LLM application — invented facts, fake citations, non-existent policies — and show they…

Detect direct and indirect prompt-injection attempts and successful policy breaks against an LLM application from prompt/response telemetry.

Elicit sensitive information an LLM application should not reveal — training data, other users' data, secrets pulled into context, or…