The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional Markdown and static reference data. No scripts, binaries, or automated tasks were detected.
[DATA_EXPOSURE]: The skill references local context files like .agents/product-marketing.md. These are standard project metadata files used for tailoring content and do not involve sensitive system configuration or private user data.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and process external marketing context. However, this is evaluated as safe because the skill has no dangerous capabilities (such as shell access, network operations, or file-writing tools) that could be exploited via malicious input in those files.
Ingestion points: product-marketing-context.md and similar context files (SKILL.md).
Boundary markers: Absent.
Capability inventory: None (the skill defines no tools or executable scripts).
Sanitization: Absent.

copywriting