Security Audit

logo-dev-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

logo-dev-automation received a trust score of 88/100, 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 Potential for Command Injection and Excessive Permissions via Rube MCP Tool 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 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

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential for Command Injection and Excessive Permissions via Rube MCP Tool Execution The skill provides an interface to execute external tools via `RUBE_MULTI_EXECUTE_TOOL` and perform 'bulk operations' via `RUBE_REMOTE_WORKBENCH` using `run_composio_tool()`. The security posture of this skill is highly dependent on the underlying `rube` MCP and the `logo_dev` toolkit. If these external tools or the workbench environment are not properly sandboxed, or if they allow for arbitrary command execution, file system access, or network requests beyond the intended scope of 'Logo Dev operations', an attacker could leverage this skill to perform command injection, access sensitive data, or execute actions with excessive permissions. The documentation does not specify the security boundaries, sandboxing, or strict limitations on the capabilities of the executed tools, particularly for `RUBE_REMOTE_WORKBENCH`. Ensure that the `rube` MCP and the `logo_dev` toolkit strictly sandbox executed tools, limit their access to system resources (filesystem, network), and validate all arguments to prevent command injection. Implement robust input validation and authorization checks for all tool arguments. Clearly document the security boundaries and capabilities of `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`, explicitly stating any limitations on arbitrary code execution or system access.	LLM	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/f341aec09647a2b8.svg)](https://skillshield.io/report/f341aec09647a2b8)