apify-product-lookup
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external retailer websites, creating a potential surface for indirect prompt injection attacks. 1. Ingestion points: The skill uses the
get-dataset-itemstool to fetch product details and marketing text from arbitrary product pages. 2. Boundary markers: The instructions lack explicit requirements for using delimiters or 'ignore embedded instructions' warnings when processing this external content. 3. Capability inventory: The skill's functionality is focused on data retrieval; it does not request dangerous capabilities such as file system writes or shell command execution. 4. Sanitization: No specific filtering or sanitization steps are defined for the incoming retailer data. - [EXTERNAL_DOWNLOADS]: The skill connects to the Apify MCP server at
https://mcp.apify.comto execute its primary functions. This represents a connection to a well-known service for its intended purpose.
Audit Metadata