Security Audit

fluxguard-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

fluxguard-automation received a trust score of 73/100, 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 Excessive Tool Access via Generic Rube MCP Execution.

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

70%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

2 findings

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Excessive Tool Access via Generic Rube MCP Execution The skill leverages generic Rube MCP execution tools, specifically `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`. These tools are designed to discover and execute a wide range of operations available through the Rube MCP ecosystem, not just Fluxguard-specific tasks. This grants the skill, and by extension the agent using it, overly broad access to potentially any tool or capability exposed by Rube MCP, which could include tools with system, network, or sensitive data access beyond the intended scope of Fluxguard automation. Implement fine-grained access control within the Rube MCP system to restrict the set of tools discoverable and executable by this skill to only those strictly necessary for Fluxguard automation. Alternatively, the skill's instructions should be refined to only expose and guide the use of Fluxguard-specific tools, rather than generic execution mechanisms that can access the entire Rube MCP ecosystem.	LLM	SKILL.md:64
HIGH	Excessive Tool Access via Generic Rube MCP Execution The skill explicitly mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This suggests the ability to execute arbitrary Composio tools through a remote workbench, which is a highly privileged operation. If `run_composio_tool()` can execute any Composio tool, and Composio tools can have broad system or data access, this constitutes excessive permissions, allowing the skill to perform actions far beyond its stated purpose of Fluxguard automation. Implement fine-grained access control within the Rube MCP system to restrict the set of tools discoverable and executable by this skill to only those strictly necessary for Fluxguard automation. Alternatively, the skill's instructions should be refined to only expose and guide the use of Fluxguard-specific tools, rather than generic execution mechanisms that can access the entire Rube MCP ecosystem.	LLM	SKILL.md:84

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/3222fb2c31340756.svg)](https://skillshield.io/report/3222fb2c31340756)