The Agent Skills Directory

[PROMPT_INJECTION]: The instructions establish a professional persona as a FastAPI expert. There are no attempts to override safety guidelines, bypass restrictions, or extract system prompts.
[EXTERNAL_DOWNLOADS]: The skill references well-known and trusted ecosystem libraries such as FastAPI, Pydantic, SQLAlchemy, and Redis. It does not include commands to download or execute code from unverified remote sources.
[CREDENTIALS_SAFE]: Code examples and templates use environment variable placeholders (e.g., DATABASE_URL) and best practices for authentication (JWT, OAuth2) without hardcoding any secrets or sensitive keys.
[DATA_EXFILTRATION]: No network operations to unknown domains or commands that access sensitive local files (like SSH keys or AWS credentials) are present.
[OBFUSCATION]: The skill's content is clear, readable, and free of encoded strings, zero-width characters, or homoglyph attacks.
[INDIRECT_PROMPT_INJECTION]: While the skill assists in building APIs that process external data, it explicitly includes security capabilities such as input sanitization, Pydantic validation, and Role-Based Access Control (RBAC) to guide the agent toward generating secure code.
[SAFE]: The overall design follows development best practices, emphasizing type safety, testing, and observability without introducing persistence mechanisms or privilege escalation risks.

fastapi-pro