Security Audit
QuickBooks Automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
QuickBooks Automation received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Broad Data Access via SQL-like Query Tool.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 20, 2026 (commit 27904475). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Broad Data Access via SQL-like Query Tool The `QUICKBOOKS_QUERY_ACCOUNT` tool allows executing 'SQL-like query strings' against QuickBooks accounts. An LLM, if prompted maliciously or without sufficient guardrails, could construct broad queries (e.g., 'SELECT * FROM Account') to retrieve and potentially exfiltrate sensitive financial data beyond the scope of an intended task. This exposes a wide range of account information, which could lead to unauthorized data disclosure. Implement strict LLM guardrails and input validation for the `query` parameter of `QUICKBOOKS_QUERY_ACCOUNT`. Limit the types of queries allowed, restrict access to sensitive fields, or enforce specific query patterns to prevent broad data retrieval. Consider using more granular tools if specific data points are needed, rather than a general query interface. | LLM | SKILL.md:90 |
Scan History
Embed Code
[](https://skillshield.io/report/c08ebb55f64750b1)
Powered by SkillShield