The Agent Skills Directory

[SAFE]: The skill's primary function is to provide systematic instructions for copy editing and word choice optimization.
[DATA_EXPOSURE]: The instructions direct the agent to check for a .agents/product-marketing-context.md file to align with brand voice. This is a standard practice for context-aware agents and does not involve exfiltration or access to sensitive system credentials.
[PROMPT_INJECTION]: While the skill ingests and processes user-provided text which could theoretically contain indirect prompt injections, the skill lacks the necessary capabilities (such as network access, file writing, or shell execution) to perform any harmful actions. The output is restricted to rewritten text.

copy-editing