Security Audit
bamboohr-automation
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
bamboohr-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 Access to Sensitive Employee PII and HR Operations.
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 e36d6fd3). 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 Access to Sensitive Employee PII and HR Operations The skill provides extensive access to BambooHR's API, enabling operations such as retrieving all employee data (`BAMBOOHR_GET_ALL_EMPLOYEES`, `BAMBOOHR_GET_EMPLOYEE`), sensitive dependent information (`BAMBOOHR_DEPENDENTS_GET_ALL`), benefit coverages (`BAMBOOHR_BENEFIT_GET_COVERAGES`), and updating employee profiles (`BAMBOOHR_UPDATE_EMPLOYEE`). The skill documentation explicitly highlights the sensitive nature of this data, including PII like SSN. Granting an LLM agent such broad access to critical HR systems without stringent guardrails creates a high risk of unauthorized data access, modification, or potential exfiltration if the agent is compromised or misused through prompt injection. Implement the principle of least privilege by configuring the underlying BambooHR API key (used by Rube MCP) with the minimum necessary permissions for the skill's intended function. Consider breaking this monolithic skill into smaller, more specialized skills, each with a narrower scope of access. Additionally, ensure robust prompt engineering, output filtering, and human-in-the-loop verification are in place for any LLM agent utilizing this skill to prevent misuse of sensitive data. | LLM | SKILL.md:110 |
Scan History
Embed Code
[](https://skillshield.io/report/3f1cf5d60cb4ccdd)
Powered by SkillShield