Security Audit

breeze-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

breeze-automation received a trust score of 86/100, 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 Reliance on external, unverified MCP service.

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

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Reliance on external, unverified MCP service The skill's manifest declares a dependency on 'rube' MCP, and the skill documentation explicitly directs interaction with an external Multi-Cloud Platform (MCP) service hosted at `https://rube.app/mcp`. All core functionality (tool discovery, connection management, and tool execution for Breeze operations) is routed through this third-party service. The security and trustworthiness of `rube.app` are external to this skill package and cannot be verified by the skill itself. A compromise or malicious intent of this external service could lead to data exfiltration, unauthorized actions, or other security breaches when the LLM uses this skill. Assess the trustworthiness and security posture of `rube.app`. If possible, use an MCP that can be self-hosted, audited, or is provided by a highly trusted vendor. Implement robust input validation and output sanitization for all interactions with the external MCP. Consider adding mechanisms to verify the integrity of the MCP's responses and tool schemas.	LLM	SKILL.md:14

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e643afdba77a6229.svg)](https://skillshield.io/report/e643afdba77a6229)