Security Audit

jumpcloud-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

jumpcloud-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 Dynamic Tool Discovery and Execution from External Source.

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

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Dynamic Tool Discovery and Execution from External Source The skill instructs the LLM to dynamically discover tools and their schemas from the external Rube MCP (`RUBE_SEARCH_TOOLS`) and subsequently execute them (`RUBE_MULTI_EXECUTE_TOOL`). This design means the effective permissions and capabilities of the skill are entirely dictated by the Rube MCP at runtime. If the Rube MCP is compromised, provides malicious tool definitions, or exposes overly broad functionality, the LLM could be instructed to perform arbitrary, potentially harmful actions on the connected Jumpcloud instance or other systems accessible via Rube. The skill itself does not define or limit the scope of operations, making it a conduit for any functionality exposed by the Rube MCP, which represents a significant supply chain risk. Implement a whitelist or strict validation of tool slugs and arguments that can be executed via the Rube MCP. The skill definition should ideally specify allowed tool categories or specific tool slugs, rather than allowing arbitrary discovery and execution. Alternatively, the Rube MCP itself must implement robust security measures, including tool sandboxing and strict access controls, and its integrity must be verifiable.	LLM	SKILL.md:40

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/4c0db0f11683eb96.svg)](https://skillshield.io/report/4c0db0f11683eb96)