The Agent Skills Directory

[COMMAND_EXECUTION]: The skill contains internal logic for a 'simulation mode' that explicitly prohibits the AI from using shell or file-writing tools, which acts as a functional constraint for safety.
[PROMPT_INJECTION]: The skill ingests user input for business details to populate templates. While this is a surface for indirect prompt injection, the risk is minimized as the data is used solely for local document generation.
[SAFE]: The skill references local paths and structured metadata to maintain consistency in its output without making external network requests or using unverified dependencies.

growth-acceleration