The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local script scripts/amazon_product_database.py to perform API calls and manage search results. This is the primary mechanism for the skill's operation.
[EXTERNAL_DOWNLOADS]: The Python script makes POST requests to the NexScope proxy gateway (via the NEXSCOPE_PROXY_BASE endpoint) to retrieve Amazon product data. This connection to the vendor's API is necessary for the product research functionality.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from the Amazon product database, which serves as a potential vector for indirect prompt injection.
Ingestion points: The skill ingests external content such as product titles, brands, and category paths via the productDatabaseList API response in scripts/amazon_product_database.py.
Boundary markers: The data is received in structured JSON, but individual text fields (e.g., product titles) are presented to the agent without explicit delimiters to distinguish them from instructions.
Capability inventory: The skill possesses the capability to make network requests to the NexScope API and write search result files to the project's local nexscope/ directory.
Sanitization: The script performs standard JSON parsing of the API response but does not implement specific sanitization or filtering of the text content before it is displayed to the agent.

ecommerce-amazon-product-database