The Agent Skills Directory

[SAFE]: The skill provides expert instructions and content templates for AI search engine optimization. A thorough review of the markdown instructions and reference guides revealed no malicious patterns, command execution, or unauthorized data access.
[INDIRECT_PROMPT_INJECTION]: The skill includes instructions to ingest data from project-specific context files and user-provided search queries to tailor its advice. While this represents a data ingestion surface, the access is restricted to standard agent workspace paths and the skill lacks any capabilities to execute commands or exfiltrate data.
Ingestion points: Project files located at .agents/product-marketing-context.md or .claude/product-marketing-context.md, as well as user content intended for SEO optimization.
Boundary markers: The instructions do not define specific delimiters for external content.
Capability inventory: The skill contains no executable code, shell scripts, or tool definitions; it is purely instructional.
Sanitization: No sanitization methods are specified for the processed content.

ai-seo