Security Audit

qualaroo-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

qualaroo-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 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Reliance on unverified third-party MCP service.

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

85%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Reliance on unverified third-party MCP service The skill explicitly relies on the 'Rube MCP' service hosted at `https://rube.app/mcp` for all its functionality, as indicated in the setup instructions and the manifest's `requires` section. This introduces a significant supply chain risk, as the security and integrity of the skill's operations are entirely dependent on the trustworthiness and security posture of this external service. A compromise of `rube.app` or the Qualaroo toolkit provided by Composio could lead to unauthorized access to Qualaroo data or the execution of arbitrary actions within Qualaroo via the `RUBE_MULTI_EXECUTE_TOOL`. Evaluate the security posture and trustworthiness of `rube.app` and Composio. Consider implementing additional validation or sandboxing mechanisms for responses from the Rube MCP, if possible. Ensure that the LLM's permissions are scoped to only what is necessary for interacting with the Rube MCP and Qualaroo, and that any sensitive data handled by Qualaroo is appropriately protected.	Static	SKILL.md:20

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/2ed373071129c202.svg)](https://skillshield.io/report/2ed373071129c202)