billing-automation
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or unauthorized network operations were detected. The skill focuses on legitimate business automation tasks and includes safety warnings regarding the use of sandbox environments.\n- [PROMPT_INJECTION]: The skill provides templates for generating HTML invoices and emails using customer-supplied data (such as name and address). This represents a surface for indirect prompt injection. While acceptable in an illustrative implementation guide, developers using these patterns should implement sanitization and boundary markers to ensure untrusted inputs do not influence agent behavior.\n
- Ingestion points: Customer attributes used in the
Invoice.to_htmlandDunningManager.send_dunning_emailmethods inresources/implementation-playbook.md.\n - Boundary markers: Absent in the provided code samples.\n
- Capability inventory: The code demonstrates payment processing via the Stripe API and unimplemented email-sending logic.\n
- Sanitization: Not explicitly shown in the provided boilerplate code.
Audit Metadata