The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the review of external Django projects, which introduces a vulnerability surface for indirect prompt injection if the source code being analyzed contains malicious instructions.
Ingestion points: Project configuration and source files (e.g., models.py, settings.py) are ingested using the Read, Grep, and Glob tools during the code review process.
Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded instructions within the code being analyzed.
Capability inventory: The skill allows the use of Read, Write, Grep, and Glob tools.
Sanitization: No explicit sanitization or filtering of the analyzed content is provided in the instructions.

django-conventions