quickbooks

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs all its operations, including setup, authentication, and data retrieval, by executing a local script (quickbooks.ts) via the npx tsx runner. This is a standard functional pattern for this type of integration.\n- [PROMPT_INJECTION]: The skill ingests data from the QuickBooks Online API, creating a surface for potential indirect prompt injection attacks if the accounting data contains malicious instructions.\n
  • Ingestion points: External data is ingested from QuickBooks Online API endpoints via the quickbooks.ts script (SKILL.md).\n
  • Boundary markers: The instructions do not define specific delimiters or boundary markers for the ingested data.\n
  • Capability inventory: The skill has the capability to execute local scripts and access the local filesystem for credential management.\n
  • Sanitization: No explicit sanitization or filtering of external API content is documented in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 12:31 AM
Security Audit — agent-trust-hub — quickbooks