connect-ai-quickbooksonline

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of data from QuickBooks Online, which is an external and potentially untrusted source.
  • Ingestion points: Data is retrieved from various QuickBooks tables including Accounts, Customers, Vendors, Invoices, and PurchaseLineItems as specified in SKILL.md.
  • Boundary markers: The skill does not instruct the agent to use specific delimiters or protective framing when presenting or processing the retrieved data.
  • Capability inventory: The agent is granted capabilities to perform data manipulation (INSERT, UPDATE), transactional changes (VoidInvoice), and communications (SendInvoice). This capability tier increases the risk if malicious instructions are embedded in the source data.
  • Sanitization: There are no requirements for the agent to sanitize, validate, or escape the content of fields such as Line_Description or PrivateNote before use.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 02:09 PM
Security Audit — agent-trust-hub — connect-ai-quickbooksonline