Security Audit

leverly-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

leverly-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 2 findings: 0 critical, 0 high, 1 medium, and 1 low severity. Key findings include Broad Tool Execution Capabilities, Unpinned Rube MCP Dependency.

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

91%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
MEDIUM	Broad Tool Execution Capabilities The skill utilizes `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` which allow the execution of arbitrary Leverly operations and Composio tools. While necessary for the skill's functionality to automate Leverly tasks, this grants the LLM broad access to perform any action available through the Leverly API via Composio. A compromised LLM could potentially misuse these capabilities to perform unauthorized actions. Implement granular access controls within the Rube MCP or Composio platform to limit the scope of operations available to specific skill instances or LLM contexts, if possible. Ensure the LLM is robustly secured against prompt injection to prevent misuse of these powerful tools.	LLM	SKILL.md:52
LOW	Unpinned Rube MCP Dependency The skill's manifest specifies `rube` as a required MCP without a version constraint. While `rube` refers to an MCP service (`https://rube.app/mcp`) rather than a traditional software package, the lack of a specific version or identifier in the `requires` field means that changes to the `rube` MCP service could potentially introduce breaking changes or vulnerabilities without explicit awareness or control from the skill's definition. If the platform supports versioning or specific identifiers for MCP dependencies, update the manifest to pin the `rube` MCP to a known stable and secure version. Otherwise, ensure robust monitoring and vetting of the `rube.app` service.	LLM	SKILL.md:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/70e081edc26e6a89.svg)](https://skillshield.io/report/70e081edc26e6a89)