The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the WordPress site and WooCommerce database, creating a surface for indirect injection attacks.
Ingestion points: Data is retrieved via wordpress_get_page to scan checkout pages and woocommerce_list_orders for store data review (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the site data.
Capability inventory: The skill employs tools with access to sensitive business and customer data, including woocommerce_list_orders and woocommerce_sales_report (SKILL.md).
Sanitization: No explicit sanitization or validation of external content is specified in the skill body.
[SAFE]: The skill's functionalities and external references to the developer's domain (respira.press) are consistent with its stated purpose of store auditing and diagnostics. No persistence, obfuscation, or privilege escalation patterns were found.

woocommerce-health-check