The Agent Skills Directory

[SAFE]: The skill is purely instructional and provides guidance on documentation hierarchy, navigation, and content organization. No malicious patterns were identified.
[DATA_EXPOSURE]: The skill suggests reading .claude/product-marketing-context.md or .cursor/product-marketing-context.md for context. This is a common practice for LLM agents to understand the local project context and does not involve accessing sensitive system files like SSH keys or environment variables.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests data from external context files, it lacks dangerous capabilities (no command execution, file writing, or network access), meaning any potential injection in those files would have no exploitable impact within the scope of this skill.

docs-page-generator