The Agent Skills Directory

[SAFE]: The skill instructions and referenced documents consist entirely of marketing analysis frameworks and best practices. There are no executable scripts, commands, or remote dependencies.
[DATA_EXPOSURE]: The skill is designed to read project-specific context from files like .agents/product-marketing.md. This is a standard and safe practice for providing relevant AI assistance based on the local project environment.
[INDIRECT_PROMPT_INJECTION]: The skill is intended to process external marketing URLs provided by the user. While processing untrusted web content is a known attack surface for indirect prompt injection, this skill does not include any automated processing of such data into high-privilege commands, and the inherent risk is low for this specific use case.

cro