The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides templates for loading external data files and creating command-line tools, which defines a potential attack surface for indirect prompt injection if the resulting library is used to process untrusted data within an agentic pipeline.
Ingestion points: src/my_package/loader.py (Pattern 11) demonstrates loading JSON configuration and text data from package resources using importlib.resources.files.
Boundary markers: The provided templates do not include specific delimiters or instructions to ignore embedded commands within the ingested data files.
Capability inventory: The skill demonstrates creating CLI entry points (project.scripts in Pattern 4) and building C extensions (Pattern 13), providing a mechanism for command execution.
Sanitization: The example code for loading package data does not demonstrate input validation, schema enforcement, or sanitization of the ingested content.

python-packaging