The Agent Skills Directory

[SAFE]: The skill provides standard Django administration configuration templates and best practices. No code is executed directly by the skill; it provides snippets for developer use.
[INDIRECT_PROMPT_INJECTION]: The skill includes a step to read from a local context file (.agents/django-project-context.md) to adapt its recommendations.
Ingestion points: Reads .agents/django-project-context.md in the Initial Assessment section.
Boundary markers: None present.
Capability inventory: The skill does not possess capabilities for network operations, file writing, or subprocess execution.
Sanitization: No specific sanitization or filtering of the context file content is performed.
[DATA_EXPOSURE]: No hardcoded credentials, sensitive file access (outside of local project metadata), or exfiltration patterns were identified.

django-admin