skills/nexscope-ai/nexscope-ecommerce-skills/ecommerce-amazon-product-price-series/Gen Agent Trust Hub
ecommerce-amazon-product-price-series
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests Amazon product metrics from an external API, which represents a surface for indirect prompt injection if the product data contains instructions designed to influence the agent.
- Ingestion points: Product data is retrieved via
scripts/amazon_product_price_series.pyfrom a remote Keepa proxy API. - Boundary markers: The skill includes specific instructions for trend summarization and tabular data presentation to maintain structure.
- Capability inventory: The skill performs network requests to a configured proxy and writes data to a dedicated
nexscope/directory within the project. - Sanitization: Data is parsed as structured JSON, and the script implements a summarization strategy for large responses to prevent context poisoning.
- [COMMAND_EXECUTION]: The skill operates by executing a local Python script (
scripts/amazon_product_price_series.py) which processes input parameters and facilitates communication with the Keepa API proxy. - [EXTERNAL_DOWNLOADS]: The Python script makes network requests to an external API endpoint. The endpoint is defined by environment variables and is part of the vendor's (
nexscope-ai) infrastructure, used strictly for retrieving the requested product time-series data.
Audit Metadata