The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external websites (Google Shopping, Amazon, and general web scraping via Firecrawl) which could contain malicious instructions.
Ingestion points: Data enters the context via google_shopping_bulk_products, amazon_bulk_product_details, and firecrawl_scrape tools described in SKILL.md.
Boundary markers: The instructions do not explicitly mandate the use of delimiters or specific XML tags to isolate external content from the agent's instructions, although it advises separating observations from analysis.
Capability inventory: The skill uses tools for information retrieval and structured data extraction. It does not include tools for arbitrary code execution, file system modification, or network requests to arbitrary endpoints.
Sanitization: There are no explicit instructions for sanitizing or filtering the content retrieved from external sources before processing.

competitive-pricing