Security Audit

cults-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

cults-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 Dynamic Tool Execution from Third-Party MCP.

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

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Dynamic Tool Execution from Third-Party MCP The skill's core functionality is entirely dependent on a third-party Managed Control Plane (MCP) located at `https://rube.app/mcp`. The skill explicitly instructs the LLM to dynamically discover available tools using `RUBE_SEARCH_TOOLS` and then execute them via `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH`. This means the actual actions performed by the skill are not statically defined within the skill package but are fetched at runtime from an external service. A compromise of the Rube MCP or its tool registry could lead to the injection of malicious tools, allowing arbitrary code execution, data exfiltration, or other harmful actions through the LLM without direct modification of the skill package itself. This introduces a significant supply chain risk. Implement strict vetting and continuous monitoring of third-party MCPs and their tool registries. Configure the LLM to validate tool schemas and execution plans returned by `RUBE_SEARCH_TOOLS` against a whitelist or known safe patterns before execution. Consider sandboxing the execution environment for dynamically loaded tools to limit potential damage. Implement strong access controls and authentication for the MCP connection.	LLM	SKILL.md:35

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/cb31f9d20327f1fc.svg)](https://skillshield.io/report/cb31f9d20327f1fc)