Security Audit

waboxapp-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

CAUTION

Scanned 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

waboxapp-automation received a trust score of 70/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Reliance on external, powerful meta-tool (Rube MCP), Excessive permissions via broad meta-tool access.

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 17, 2026 (commit 99e2a295). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

70%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

2 findings

Dynamic Code

1 finding

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Reliance on external, powerful meta-tool (Rube MCP) The skill explicitly requires and instructs the user to connect to 'https://rube.app/mcp' as an external MCP server. This makes the skill entirely dependent on the security and integrity of the Rube MCP service. If the Rube MCP is compromised or malicious, this skill acts as a direct conduit for arbitrary tool execution and data access, as Rube MCP is designed to discover, manage, and execute other tools dynamically. This introduces a significant supply chain risk, as the skill's functionality and security are directly tied to a third-party service. Users should be made aware of the trust implications of integrating external MCPs. Developers should consider if more granular permissions or a sandboxed environment for such meta-tools can be implemented, or if the dependency can be more tightly controlled (e.g., specific versions, cryptographic verification of the MCP endpoint).	Static	SKILL.md:15
HIGH	Excessive permissions via broad meta-tool access The skill's manifest requires access to the 'rube' MCP. The Rube MCP is a meta-tool capable of discovering, managing connections for, and executing any other tool it exposes (e.g., Waboxapp, and potentially other toolkits). This grants the skill extremely broad permissions, effectively allowing it to perform any action that Rube MCP can facilitate through its exposed tools, including `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. This creates a large attack surface, as a compromised Rube MCP or a malicious tool exposed by Rube could be leveraged through this skill to perform unauthorized actions or exfiltrate data. If possible, skills should request access to specific toolkits or individual tools rather than a generic, powerful meta-tool like Rube. Rube MCP itself should implement more granular permission scoping to limit the actions a skill can perform, even when granted access to Rube.	Static	SKILL.md:40

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/87091cb796529d62.svg)](https://skillshield.io/report/87091cb796529d62)