The Agent Skills Directory

[SAFE]: The skill consists exclusively of instructional markdown files and YAML-based data templates designed for content generation. It does not contain any scripts, executables, or commands.
[DATA_EXPOSURE]: The skill references standard agent context files, such as .agents/product-marketing-context.md, to gather business context. This is a standard practice for personalizing agent output and does not involve exfiltrating sensitive data or accessing unauthorized file paths.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided data about products and competitors to generate marketing copy. While it does not explicitly define sanitization logic, the lack of any powerful tool access or shell execution capabilities within the skill makes it resilient against indirect prompt injection attacks.

competitor-alternatives