The Agent Skills Directory

[SAFE]: The skill serves as a developer guide for integrating third-party plugins with Rank Math's JSON-LD graph. It uses standard WordPress hooks and functions (add_filter, get_post_meta, esc_url_raw).
[INDIRECT_PROMPT_INJECTION]: The skill describes processing external data (WordPress post metadata and titles). However, it mitigates potential risks by providing explicit instructions to sanitize and validate data using functions like wp_strip_all_tags and esc_url_raw. It also includes a dedicated 'Security and privacy' section that warns against leaking private data or accepting arbitrary JSON-LD.
[METADATA_POISONING]: The metadata in the YAML frontmatter and the OpenAI agent configuration is consistent with the skill's purpose and does not contain any deceptive instructions.

rankmath-schema-integration