The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources including competitor pricing pages, Google Shopping, and Amazon listings.
Ingestion points: Data enters the agent's context through tools like firecrawl_scrape, strale_pricing_page_extract, google_shopping_bulk_products, and amazon_bulk_product_details defined in SKILL.md and references/sandbase-api-map.md.
Boundary markers: The instructions lack explicit delimiters or safety guidelines directing the agent to ignore instructions embedded within the scraped content.
Capability inventory: The skill has capabilities to perform web scraping and data extraction through the SandBase gateway.
Sanitization: There is no evidence of sanitization or validation of the external content before it is processed by the agent.

competitive-pricing