ecommerce-amazon-product-discovery
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes product information from the Amazon marketplace. Since this content is controlled by external sellers, it represents a potential vector for indirect prompt injection attacks where instructions could be embedded in product data to manipulate the agent's behavior.
- Ingestion points: External data is ingested through the Jiimore API via
scripts/amazon_product_discovery.py. - Boundary markers: None. The skill's instructions do not include specific delimiters or directives to ignore instructions that might be contained within the product data.
- Capability inventory: The skill has capabilities for network operations and local file system writes (caching and session data storage) through the execution of
scripts/amazon_product_discovery.py. - Sanitization: The script correctly handles the JSON structure of the API response but does not sanitize or filter the content of the text fields (such as product titles) before they are passed into the agent's context.
Audit Metadata