The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to use a terminal tool to run test commands such as pytest tests/test_feature.py::test_specific_behavior -v and pytest tests/ -q. This is a standard and expected functionality for a development-focused skill.
[INDIRECT_PROMPT_INJECTION]: The skill processes and acts upon external data (source code and test suites) which it ingests into the agent's context. This presents a surface for indirect prompt injection if the processed files contain malicious instructions.
Ingestion points: The skill reads source files and test scripts throughout the development cycle as part of the RED-GREEN-REFACTOR process.
Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the codebase being processed.
Capability inventory: The skill utilizes the terminal tool for executing shell commands, the file tool for modifying project files, and the delegate_task tool for task orchestration.
Sanitization: The skill does not specify procedures for validating or sanitizing the content of the files it manages.

test-driven-development