Security Audit

leiga-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

leiga-automation received a trust score of 93/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.

SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 1 medium, and 1 low severity. Key findings include Broad tool execution capability via RUBE_REMOTE_WORKBENCH, 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 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

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 capability via RUBE_REMOTE_WORKBENCH The skill exposes `RUBE_REMOTE_WORKBENCH` which allows for `run_composio_tool()`. This suggests a generic mechanism for executing arbitrary Composio tools. The scope of actions possible through `run_composio_tool()` is not defined within the skill, potentially granting the agent broad permissions if the underlying Composio tools have extensive capabilities (e.g., access to sensitive data, system modification, or interaction with many external services). This increases the attack surface if the agent is compromised or misused. If possible, restrict the capabilities of `RUBE_REMOTE_WORKBENCH` to only necessary operations for the Leiga toolkit, or provide more granular tool access instead of a generic `run_composio_tool()` if the underlying platform allows. Ensure that the Composio tools themselves adhere to the principle of least privilege.	LLM	SKILL.md:80
LOW	Unpinned Rube MCP dependency The skill manifest declares a dependency on the 'rube' MCP (`"mcp": ["rube"]`) without specifying a version. This means the skill will always use the latest available version of the Rube MCP. While common for MCPs, this introduces a supply chain risk where a malicious or buggy update to the Rube MCP could automatically affect this skill without explicit review or pinning, potentially leading to unexpected behavior or security vulnerabilities. If the platform supports it, specify a minimum or exact version for the `rube` MCP dependency to ensure stability and prevent unexpected changes from upstream updates. Regularly review and update dependencies.	LLM	SKILL.md

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/dc5d780832bf7805.svg)](https://skillshield.io/report/dc5d780832bf7805)