Security Audit

gosquared-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

gosquared-automation received a trust score of 78/100, 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 Reliance on external Rube MCP introduces supply chain risk, Broad tool execution capability via RUBE_MULTI_EXECUTE_TOOL.

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

78%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Reliance on external Rube MCP introduces supply chain risk The skill explicitly relies on an external Managed Control Plane (MCP) hosted at `https://rube.app/mcp` and `https://composio.dev`. All Gosquared operations are mediated through this third-party service. A compromise of the Rube MCP infrastructure or the Composio platform could lead to unauthorized access, data manipulation, or exfiltration of data from connected Gosquared accounts. The skill itself does not provide any mechanisms to verify the integrity or security of this external service, making its security a critical dependency. Implement robust vetting processes for third-party services. Consider sandboxing the execution environment for skills interacting with external MCPs. Monitor network traffic for unusual activity and ensure the external service adheres to strict security standards.	Static	SKILL.md:15
MEDIUM	Broad tool execution capability via RUBE_MULTI_EXECUTE_TOOL The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` to perform Gosquared operations. While `RUBE_SEARCH_TOOLS` is recommended for schema discovery, the `RUBE_MULTI_EXECUTE_TOOL` itself, as described, does not appear to have inherent granular access controls defined within the skill's context. This means the LLM, once connected to Gosquared via Rube MCP, could potentially be instructed to perform any operation available through the Gosquared API, limited only by the permissions of the connected Gosquared account and the Rube MCP toolkit's implementation. This broad access could be exploited if the LLM is prompted maliciously or makes an erroneous decision, leading to unintended or unauthorized actions within Gosquared. Implement fine-grained access control policies for the Gosquared connection within Rube MCP, if available. Restrict the scope of operations that the LLM can request through the `RUBE_MULTI_EXECUTE_TOOL` to only those strictly necessary for the skill's intended purpose. Consider adding an approval step or human-in-the-loop for sensitive operations.	Static	SKILL.md:40

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/19a4688d118886f7.svg)](https://skillshield.io/report/19a4688d118886f7)