The Agent Skills Directory

[SAFE]: The skill's functionality is limited to generating text-based recommendations and strategy advice. It does not contain any scripts, binaries, or commands that could compromise system security.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to read a local context file, specifically .agents/product-marketing-context.md, to tailor its marketing advice. While this introduces an external data ingestion point, the risk of exploitation is negligible because the skill lacks high-privilege capabilities such as shell access, file system modification, or network requests.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill does not attempt to access sensitive files or credentials. The context file it reads is a project-specific resource provided by the user and does not contain sensitive system information. No network transmission patterns were detected.

marketing-psychology