The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify existing Django project files, creating an attack surface for indirect instructions hidden in project data.
Ingestion points: The skill processes local files such as settings.py, models.py, and manage.py in SKILL.md.
Boundary markers: The instructions lack specific delimiters or warnings to ignore potentially malicious instructions embedded in comments or data within the files being analyzed.
Capability inventory: The skill utilizes subprocess calls for database migrations and file-writing capabilities for generating Django components.
Sanitization: No explicit sanitization or filtering is defined for external code or configuration content ingested by the agent.
[COMMAND_EXECUTION]: The skill workflow requires the execution of shell commands to manage the application lifecycle.
Evidence: The core workflow in SKILL.md instructs the agent to run python manage.py makemigrations and python manage.py migrate.
Evidence: The skill suggests validating API endpoints using curl checks.
[EXTERNAL_DOWNLOADS]: The skill references external resources for supplementary documentation.
Evidence: SKILL.md contains a link to https://jeffallan.github.io/claude-skills/skills/backend/django-expert/. This domain is an official resource associated with the skill author on a well-known hosting service.

django-expert