The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes site metadata, URLs, and sitemap paths from Google Search Console, which could theoretically contain malicious instructions if a property is shared by an untrusted party.
Ingestion points: Site lists and sitemap data are retrieved via list_sites and list_sitemaps as defined in SKILL.md.
Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the retrieved data.
Capability inventory: The skill has the ability to modify or delete properties using update_site and delete_site as seen in SKILL.md.
Sanitization: Branded keywords are validated for regex compilation, but other string inputs from tool outputs are not explicitly sanitized.

property-setup