openapi-invoicing

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references external documentation and OpenAPI specification files hosted on official vendor domains, specifically docs.openapi.it and console.openapi.com. These resources are used to define the API structures for invoicing and payment services.
  • [DATA_EXFILTRATION]: The skill communicates with several vendor-owned API endpoints including invoice.openapi.com, sdi.openapi.it, and ws.pagasubito.it to transmit and retrieve financial and fiscal data. These operations are consistent with the skill's primary purpose and involve legitimate vendor infrastructure.
  • [PROMPT_INJECTION]: The skill ingests untrusted external data through endpoints designed to import invoices (/IT-invoices_import, /customer_invoice_imports), which represents an indirect prompt injection surface.
  • Ingestion points: XML or JSON invoice data processed via the import and creation endpoints.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands within the processed data are provided in the skill instructions.
  • Capability inventory: The skill possesses the ability to make network requests and monitor the state of financial transactions through the provided APIs.
  • Sanitization: The instructions do not define specific sanitization or validation protocols for the content of the imported fiscal documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 12:17 PM
Security Audit — agent-trust-hub — openapi-invoicing