ecommerce-1688-product-search
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local Python script located at
scripts/1688_product_search.pyto handle API communication, result caching, and data persistence. The script uses standard Python libraries and operates within the expected scope of the skill's research functionality. - [EXTERNAL_DOWNLOADS]: The Python script makes network requests to a remote API endpoint. These requests target the vendor's infrastructure (configured via
NEXSCOPE_PROXY_BASE) to retrieve 1688 product data, which is the primary function of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted third-party product data (such as titles, descriptions, and supplier names) sourced from the 1688 marketplace.
- Ingestion points: Data is received from the
/api/v1/tools/research/dld/productSearchendpoint and read into the agent's context through the script's output. - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the retrieved product data.
- Capability inventory: The associated script has the capability to perform network operations and write to the local filesystem within the current working directory or home directory.
- Sanitization: There is no evidence of content filtering or sanitization applied to the external API response before it is processed by the agent.
Audit Metadata