The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a project-specific migration command (defaulting to python manage.py sqlmigrate) to retrieve the generated SQL for a migration. This is an essential feature for the skill to accurately assess database safety by inspecting the actual DDL statements produced by the Django ORM.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted data from migration files and shell command output. Ingestion points: The agent reads migration files (referenced in SKILL.md Mode 1, Step 1) and the output of the sqlmigrate command (referenced in SKILL.md Mode 1, Step 2). Boundary markers: The instructions do not define specific delimiters or warnings for the processed data. Capability inventory: The skill can execute shell commands and generate new migration files (all scripts). Sanitization: There is no explicit sanitization of the external content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill includes references to external documentation and open-source libraries (e.g., PostgreSQL documentation, django-pg-zero-downtime-migrations on GitHub). These references are used for educational purposes and to provide context for migration safety rules.

django-safe-migration