shop-customer-insights
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from customer records and order histories which may contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Untrusted data enters the context via the
shop_list_customersandshop_list_orderstools. - Boundary markers: The skill uses a structured Markdown template to separate different analysis outputs.
- Capability inventory: The skill possesses the ability to modify loyalty tiers through
shop_update_loyaltyand initiate broadcasts viashop_create_push_broadcast. - Sanitization: The skill implements a human-in-the-loop guardrail by requiring line-by-line user validation for all loyalty updates, which helps mitigate automated exploitation.
Audit Metadata