Security Audit

paradym-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

paradym-automation received a trust score of 86/100, 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 Unverified external MCP dependency (`rube.app`).

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

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Unverified external MCP dependency (`rube.app`) The skill's core functionality relies entirely on an external, unverified Managed Control Plane (MCP) hosted at `https://rube.app/mcp`. The skill's manifest explicitly requires `{"mcp": ["rube"]}` and the documentation instructs users to add this endpoint. If `rube.app` is compromised or becomes malicious, it could provide harmful tool schemas, redirect users to phishing sites during authentication, or execute arbitrary code/exfiltrate data through the `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH` calls. There is no mechanism within the skill to verify the integrity or trustworthiness of the Rube MCP, making the entire skill's security posture dependent on this external service. Implement mechanisms to verify the integrity and trustworthiness of external MCPs. Consider sandboxing or restricting the capabilities of tools provided by external MCPs. Provide clear warnings to users about the risks of relying on unverified external services. For critical applications, consider self-hosting or using a trusted, audited MCP.	LLM	SKILL.md:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/faa0b03d5d77ad80.svg)](https://skillshield.io/report/faa0b03d5d77ad80)