quickbooks-online-mcp-server

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation instructions require cloning the server source code from Intuit's official GitHub repository (github.com/intuit/quickbooks-online-mcp-server.git).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the QuickBooks Online API, which serves as a potential surface for indirect prompt injection.
  • Ingestion points: Data is ingested into the agent context through tools that retrieve QuickBooks entities (e.g., Customers, Invoices, Vendors) and financial reports.
  • Boundary markers: The skill does not provide specific delimiters or instructions for the agent to distinguish between its own system instructions and natural language content found within QuickBooks data fields.
  • Capability inventory: The skill exposes 144 tools, including significant write and delete permissions such as create_invoice, delete_invoice, and update_customer, which could be abused if an injection occurs.
  • Sanitization: There is no evidence of data sanitization or validation routines to filter malicious instructions embedded in the financial data returned by the API.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:43 PM
Security Audit — agent-trust-hub — quickbooks-online-mcp-server