Security Audit

moxie-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

moxie-automation received a trust score of 81/100, 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, 1 high, 1 medium, and 0 low severity. Key findings include Broad tool execution via Rube MCP, 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

78%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

2 findings

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad tool execution via Rube MCP The skill allows the LLM to discover and execute any tool available through the Rube MCP for Moxie operations using `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. This grants the LLM the full scope of permissions associated with the connected Moxie account, without specific constraints on operations. An attacker could craft prompts to execute sensitive or destructive Moxie operations if the underlying tools permit. Implement granular access controls within the Rube MCP or Moxie integration to restrict the types of operations or data that can be accessed/modified by the LLM. Alternatively, provide a more constrained skill that only exposes specific, safe Moxie operations.	LLM	SKILL.md:38
MEDIUM	Unpinned Rube MCP dependency The skill relies on the Rube MCP from `https://rube.app/mcp` without specifying a version or hash. This means the skill's behavior is dependent on the current version deployed at that endpoint. Malicious updates or compromises of the `rube.app` service could introduce vulnerabilities or unwanted functionality into the skill's execution environment. If possible, specify a version or hash for the Rube MCP dependency to ensure deterministic behavior and prevent unexpected changes. If direct pinning isn't supported by the MCP system, consider implementing a review process for updates from `rube.app`.	LLM	SKILL.md:19

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/48d3eb57e688598f.svg)](https://skillshield.io/report/48d3eb57e688598f)