The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill contains hardcoded passwords in multiple locations within SKILL.md.\n
Evidence: password='testpass123' in tests/conftest.py.\n
Evidence: password='adminpass123' in tests/conftest.py.\n
Evidence: password = factory.PostGenerationMethodCall('set_password', 'testpass123') in tests/factories.py.\n- [PROMPT_INJECTION]: The skill establishes a workflow for ingesting and executing tests on Django codebases, creating a surface for Indirect Prompt Injection.\n
Ingestion points: Test data and code structures from the Django application are read by the agent to generate and run tests.\n
Boundary markers: Absent. No specific delimiters or "ignore" instructions are used for user-provided code.\n
Capability inventory: The skill utilizes pytest and Django's client for database interaction and logic execution in tests/test_views.py.\n
Sanitization: Absent. There is no filtering or validation of the code being tested.

django-tdd