inttegro-customer-care

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to the official Inttegro MCP server at https://mcp.inttegro.com/ to provide customer management and messaging capabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external customer data, purchase analytics, and message delivery statuses. While this data is retrieved from authenticated Inttegro tools, the skill instructions include specific boundaries to prevent the model from attempting to reconstruct sensitive fields or perform unauthorized bulk actions.
  • Ingestion points: list_customers, get_customer, get_customer_analytics, list_payment_methods, list_messages, and get_message_analytics tools.
  • Boundary markers: Instructions explicitly state that customer IDs are the model-visible boundary and raw contact values must be withheld.
  • Capability inventory: Access is limited to authenticated Inttegro tools for customer and message management; no arbitrary shell or filesystem access is present.
  • Sanitization: The skill relies on the MCP server to provide minimized customer results and masked payment method summaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 10:55 PM