The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Google Search Console metadata, which creates a potential attack surface for indirect prompt injection.
Ingestion points: The agent ingests data including property URLs, site names, and tag names via list_sites, get_account_info, and get_cross_site_summary (SKILL.md).
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the fetched data are defined in the workflow.
Capability inventory: The skill has the ability to perform write operations, specifically managing tags via manage_tags and toggling dashboard visibility via set_dashboard_visibility (SKILL.md).
Sanitization: There is no evidence of sanitization or validation of the ingested strings before they are used in prompts or tool calls.

portfolio-overview