The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes user-provided project requirements and constraints to generate implementation patterns, creating an indirect prompt injection surface.
Ingestion points: Instructions in SKILL.md require clarifying user goals and inputs which are then used to shape the generated FastAPI code.
Boundary markers: No explicit boundary markers or instructions are provided to distinguish between the skill's trusted templates and untrusted user-provided content.
Capability inventory: The skill generates complete Python files, including database logic, API routes, and security middleware.
Sanitization: The playbook does not specify sanitization or validation methods for user-supplied data before it is interpolated into the code structure.
[SAFE]: The implementation patterns utilize industry-standard security practices, such as using environment variables via pydantic-settings for managing sensitive keys like SECRET_KEY.
[SAFE]: Authentication and security logic leverage reputable libraries including passlib (with bcrypt) for hashing and python-jose for secure JWT handling.

fastapi-templates