The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes several Python scripts (e.g., scripts/convert_to_csv.py, scripts/batch_convert_templates.py) that use subprocess.call() to execute internal format conversion logic. These calls are considered safe as they target specific local files provided within the skill package, do not use shell=True, and are used for the primary purpose of asset transformation.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to design functional test coverage based on user-supplied requirements and flows. This presents a vulnerability surface where malicious instructions could be embedded in the input data. The skill mitigates this by instructing the agent to explicitly mark assumptions and information gaps, though it lacks strict data boundary delimiters.

functional-testing