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_customers and shop_list_orders tools.
  • 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_loyalty and initiate broadcasts via shop_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
Risk Level
SAFE
Analyzed
Sep 9, 2026, 02:57 PM
Security Audit — agent-trust-hub — shop-customer-insights