Security Audit

cloudpress-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

cloudpress-automation received a trust score of 82/100, 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 Unpinned external MCP server dependency, Broad tool execution 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 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

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Unpinned external MCP server dependency The skill explicitly relies on an external Rube MCP server at `https://rube.app/mcp`. There is no mechanism described to pin the version of the MCP or its toolkits, nor any integrity checks. A compromise of `rube.app` could lead to the injection of malicious tools or altered schemas, affecting the security and functionality of the skill without the user's knowledge. Implement version pinning or integrity checks for the Rube MCP server and its toolkits. Consider hosting a trusted instance of the MCP or using a mechanism to verify the authenticity and integrity of the tools served.	LLM	SKILL.md:24
MEDIUM	Broad tool execution via `RUBE_REMOTE_WORKBENCH` The skill suggests using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This primitive implies the ability to execute potentially any Composio tool available through the Rube MCP, not just those specifically related to Cloudpress. This broad access could lead to excessive permissions if the agent is not carefully constrained, allowing it to perform actions outside the intended scope of Cloudpress automation. Clarify the scope of `run_composio_tool()` when used with `RUBE_REMOTE_WORKBENCH`. If possible, restrict the available tools to only those necessary for Cloudpress operations. Ensure the agent's permissions are granularly controlled to prevent unintended actions.	LLM	SKILL.md:80

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d4d06dd992f13716.svg)](https://skillshield.io/report/d4d06dd992f13716)