The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill describes procedures for analyzing data from external sources including CSV/JSON files, API endpoints, and database queries. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the data records. * Ingestion points: 'Data Source Assessment' section in SKILL.md. * Boundary markers: No delimiters or protective instructions are defined to separate data from commands. * Capability inventory: The skill does not request or define any executable capabilities, network tools, or file-system writing tools. * Sanitization: No input sanitization or validation logic is provided to filter potential injection strings from the data sources.
[SAFE]: The skill contains no executable scripts, binaries, or remote dependencies. The instructions are purely advisory and focused on SEO best practices.

seo-programmatic