The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and templates for content creation. It does not contain executable scripts, binary files, or commands that interact with the host system or network.
[INDIRECT_PROMPT_INJECTION]: The skill defines a prompt template that interpolates user-provided inputs such as Title, Primary Keyword, and Context. While this represents a potential surface for indirect prompt injection, the skill's lack of system-level capabilities (e.g., file writing, shell access) prevents such an injection from causing significant harm.
Ingestion points: User-defined variables in SKILL.md like {Insert Title}, {Insert Primary Keyword}, and {Insert specific context}.
Boundary markers: The input section is separated by markdown thematic breaks (---), though individual user inputs are not uniquely delimited.
Capability inventory: The skill is limited to generating text for blog posts and metadata. It has no access to sensitive environment variables, private files, or network exfiltration tools.
Sanitization: There is no explicit logic to escape or sanitize user input before it is included in the final prompt.

wordpress-centric-high-seo-optimized-blogwriting-skill