customer-360
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill refers to official Stripe documentation (https://docs.stripe.com/mcp) for setup and tool usage. This is a reference to a well-known service.
- [DATA_EXFILTRATION]: The skill is designed to access sensitive Stripe customer information, including LTV, MRR, and payment status. It incorporates specific safety constraints, such as limiting PII output and masking credit card numbers (last 4 digits only), to prevent unauthorized data exposure.
- [PROMPT_INJECTION]: The skill ingests untrusted data from Stripe API responses, which constitutes an indirect prompt injection surface.
- Ingestion points: Data enters the context through search_stripe_resources and fetch_stripe_resources in SKILL.md.
- Boundary markers: None explicitly defined to encapsulate the API response data.
- Capability inventory: The skill utilizes the stripe toolset for resource retrieval; no shell execution or network exfiltration capabilities are defined in the scripts.
- Sanitization: The workflow includes manual instructions to truncate PII and payment data before final output.
Audit Metadata