Security Audit

leverly-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

leverly-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 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Unpinned Rube MCP dependency, Broad tool execution capability 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 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

86%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Shell Execution

1 finding

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
MEDIUM	Unpinned Rube MCP dependency The skill's manifest specifies a dependency on the 'rube' MCP without a version constraint. This means the skill will always use the latest version of the Rube MCP. While this ensures access to the newest features, it also introduces a supply chain risk where breaking changes, unexpected behavior, or security vulnerabilities in a new Rube MCP version could affect the skill without explicit review or control. Pin the Rube MCP dependency to a specific version or version range in the manifest to ensure stability and allow for controlled updates and security vetting.	Static	Manifest
MEDIUM	Broad tool execution capability via RUBE_REMOTE_WORKBENCH The skill instructs the LLM on how to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`. This tool provides a generic mechanism to execute any Composio tool. While the skill's stated purpose is 'Leverly Automation', the `run_composio_tool()` function itself is not explicitly scoped to only Leverly tools within this description. If the underlying Rube MCP connection has broader permissions (e.g., access to other Composio toolkits), an LLM could potentially use this skill to execute arbitrary Composio tools beyond the intended Leverly scope, leading to excessive permissions and unintended actions. If possible, constrain the `RUBE_REMOTE_WORKBENCH` tool's capabilities within the skill's context to only allow execution of Leverly-specific tools. Additionally, ensure that the Rube MCP connection itself adheres to the principle of least privilege, granting only the necessary permissions for Leverly operations.	Static	SKILL.md:70

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d10c0b5e8414a5dd.svg)](https://skillshield.io/report/d10c0b5e8414a5dd)