Prompt Library
Manicode's prompt library contains 328 code security prompts that configure LLM coding assistants to follow secure coding patterns for specific frameworks and languages. Each prompt is a standalone markdown file that you set as the system instruction for an LLM conversation, IDE agent, or API call.
Each prompt encodes OWASP ASVS controls, CWE mitigations, and framework-specific security defaults. When active, the LLM produces code with security controls by default — parameterized queries, CSRF protection, secure session handling, and more.
Browse Prompts
🗃️ Code Security Prompts
2 items
At a Glance
| Category | Prompts | What It Covers |
|---|---|---|
| Backend Frameworks | 122 | Node.js, Python, Java, Go, .NET, PHP, Ruby on Rails, Rust, Scala, Elixir, GraphQL, gRPC, ServiceNow, SQL/RDBMS |
| Infrastructure | 54 | Secret management, Terraform, Kubernetes, Docker, serverless, WAF, CI/CD, cloud security |
| Client-Side Frameworks | 49 | React, Vue, Angular, Next.js, Svelte, TypeScript, Flutter, SolidJS, and 10 more |
| AI Security | 41 | Agentic AI, RAG security, AI agent frameworks, supply chain, governance |
| Web and API Security | 18 | SSRF, XXE, XSS, SQL injection, CSRF, CORS, JWT, WebSocket, CSP, and more |
| Auth, Crypto, Mobile, and More | 44 | Authentication, authorization, cryptography, mobile, embedded/IoT, C/C++, WASM |
Where to Start
- Find the prompt for your primary framework and deploy it to your IDE or coding agent
- Each prompt is available in up to 5 model-specific variants (Claude Opus 4.6, GPT 5.3 Codex, Gemini 3.1 Pro, Grok 4.1, GitHub Copilot)
- See Deploying Prompts for setup instructions per IDE and agent