order-lookup
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external e-commerce backend, presenting an indirect prompt injection attack surface.
- Ingestion points: Order data is retrieved via
SHOP_GET_ORDERandSHOP_SEARCH_TOOLSas described in the Quick Reference (SKILL.md). - Boundary markers: The workflow instructions do not define any delimiters or provide warnings to the agent to ignore potentially malicious instructions embedded within the retrieved order data.
- Capability inventory: The skill possesses the capability to modify order states using
SHOP_UPDATE_ORDERandSHOP_BULK_EXECUTE(SKILL.md). - Sanitization: There are no defined sanitization, validation, or filtering steps for the data processed by the agent.
Audit Metadata