Security Audit

unione-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

unione-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 Excessive Permissions via RUBE_REMOTE_WORKBENCH.

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

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill explicitly instructs the LLM about the `RUBE_REMOTE_WORKBENCH` tool, which includes the capability to execute `run_composio_tool()`. The name `run_composio_tool()` implies the ability to execute arbitrary Composio tools, not just those related to Unione. This grants the LLM excessive permissions beyond the stated scope of 'Unione automation,' potentially allowing it to interact with other toolkits or perform actions not intended for this specific skill. A malicious prompt could leverage this broad capability to execute unintended tools or actions, leading to privilege escalation or unauthorized operations. 1. Clarify the scope of `run_composio_tool()`: If it's truly generic, restrict its availability or document its specific limitations. 2. If `RUBE_REMOTE_WORKBENCH` is intended only for Unione, ensure `run_composio_tool()` is strictly scoped to only Unione tools. 3. Implement robust input validation and authorization checks within the `Rube` system for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` to prevent arbitrary tool execution or privilege escalation. 4. Consider removing `RUBE_REMOTE_WORKBENCH` from the quick reference if its broad capabilities pose an unacceptable risk for this specific skill.	LLM	SKILL.md:65

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/f907baece593f2f6.svg)](https://skillshield.io/report/f907baece593f2f6)