The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to run standard Django management commands and testing tools (makemigrations, migrate, ruff, pytest). These are expected behaviors for a development-focused skill and align with the stated purpose.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes existing project files which then influence its code generation and command execution.
Ingestion points: The agent is instructed to read src/project/ids.py, src/<app>/admin.py, and existing models or repositories as specified in the SKILL.md.
Boundary markers: Absent; there are no instructions provided to the agent to treat external project content as untrusted.
Capability inventory: The agent is granted Write, Edit, and Bash tools, which are used to apply changes and run code (e.g., migrations and tests).
Sanitization: Absent; the skill does not include logic or instructions to validate or sanitize the ingested project code.

models