Trust Assessment
quickbooks received a trust score of 88/100, 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 Potential Data Exfiltration via Malicious QB_BASE Environment Variable.
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 14, 2026 (commit 13146e6a). 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 | Potential Data Exfiltration via Malicious QB_BASE Environment Variable The skill's example `curl` commands use the `$QUICKBOOKS_ACCESS_TOKEN` in the Authorization header and construct the API endpoint using `$QB_BASE`. The `SKILL.md` suggests setting `QB_BASE` as an environment variable (`export QB_BASE="..."`). If an LLM agent executes these commands and `QB_BASE` is controlled by an attacker (e.g., through a compromised environment or malicious user input that influences environment variable setting), the `QUICKBOOKS_ACCESS_TOKEN` could be sent to an arbitrary malicious server, leading to credential exfiltration. LLM agents should validate or restrict the values of environment variables used to construct sensitive API endpoints. Specifically, `QB_BASE` should either be hardcoded within the agent's logic to the legitimate Intuit API endpoint, or if configurable, its value must be strictly validated against a whitelist of trusted domains before use. Alternatively, the skill should explicitly state that `QB_BASE` must *not* be user-controlled. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/b44914dead14fbb5)
Powered by SkillShield