The Agent Skills Directory

[SAFE]: The skill consists of purely instructional content and markdown documentation intended to guide the agent in SEO best practices. There are no executable scripts, commands, or network-bound operations included.
[DATA_EXPOSURE]: The instructions direct the agent to read local project configuration files (.claude/project-context.md and .cursor/project-context.md) to gather context about the user's project. This is standard behavior for development-focused AI agents to provide relevant assistance and does not involve transmitting data to external third parties.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data (the project context files). While it lacks explicit boundary markers or sanitization instructions, it also contains no dangerous system capabilities or write-access permissions that could be exploited via malicious content in those files.
[REMOTE_CODE_EXECUTION]: No remote code patterns, package installations, or external resource downloads are present in the skill.

content-optimization