The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides instructions and configurations for the agent to process and execute Django application code, which could lead to unintended behavior if that code contains malicious instructions.
Ingestion points: Django project files including models, views, and serializers located in the application directory and the tests folder.
Boundary markers: There are no specific boundary markers or instructions to isolate or ignore instructions that may be embedded in the processed application files.
Capability inventory: The skill involves executing code via the pytest command-line tool and writing to the local file system to generate HTML coverage reports.
Sanitization: The skill does not implement any validation or sanitization mechanisms for the user-supplied application code before it is executed as part of the test cycle.

django-tdd