ecommerce-walmart-product-detail
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests product data from external Walmart listings, creating a potential surface for indirect prompt injection. This is a standard characteristic of search and lookup tools.
- Ingestion points: Product information is retrieved via the vendor API in
scripts/walmart_product_detail.py. - Boundary markers: The skill does not employ explicit delimiters or instructions to treat the API response as untrusted data.
- Capability inventory: The skill is capable of writing to a local
nexscope/directory for caching purposes and outputting data to the agent's context. - Sanitization: There is no evidence of filtering or sanitizing the retrieved product content (such as descriptions) before it is processed by the agent.
Audit Metadata