shop-reorder-planner
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting data from potentially untrusted external sources (product names, variant descriptions, and order details).
- Ingestion points: Untrusted data enters the context through
shop_list_products,shop_get_product, andshop_list_orders(SKILL.md). - Boundary markers: There are no explicit delimiters or specific instructions to the agent to disregard instructions that might be embedded within the retrieved product or order data.
- Capability inventory: The skill's capabilities are limited to reading data; it has no access to file writing, subprocess execution, or network exfiltration outside of the authorized toolset.
- Sanitization: No explicit sanitization or escaping mechanisms are defined for the data interpolated into the final markdown report.
Audit Metadata