The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to guide an agent through the process of writing, reviewing, and modifying Django REST Framework components based on external project requirements. This workflow creates a surface for indirect prompt injection where malicious instructions could be embedded in the code snippets or requirements being processed.
Ingestion points: The skill instructs the agent to add or change DRF viewsets, serializers, and querysets based on external context described in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted inputs from the agent's core instructions.
Capability inventory: The skill context involves modifying Python source files and executing testing/linting tools such as pytest and drf-lint.
Sanitization: No specific sanitization or validation logic for external code or data inputs is mentioned.
[EXTERNAL_DOWNLOADS]: The skill references several external libraries and utilities for performance profiling and code quality.
It suggests using django-prefetch and django-zeal from the public Python Package Index (PyPI).
It references mitol-drf-lint, a tool hosted in the vendor's official GitHub repository (github.com/mitodl/ol-django).
These downloads are for legitimate, established development tools and are documented neutrally in accordance with their intended use for performance optimization.

drf-api-performance