Security Audit

cults-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

cults-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 Unpinned external MCP dependency, Broad tool execution capability 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 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

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Unpinned external MCP dependency The skill relies on an unversioned external MCP server (`https://rube.app/mcp`). This introduces a supply chain risk as the behavior, functionality, and security of the `rube` MCP can change at any time without explicit version pinning or review, potentially introducing vulnerabilities or malicious functionality. There is no mechanism to ensure the integrity or consistency of the external service. Pin the version of the Rube MCP or specify a hash/checksum for the expected MCP configuration to ensure consistent and reviewed behavior. Consider hosting critical MCP components locally or through trusted, version-controlled channels.	Static	SKILL.md:20
MEDIUM	Broad tool execution capability via RUBE_REMOTE_WORKBENCH The skill instructs the agent to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`. This tool, depending on the `rube` MCP's configuration, could allow the execution of arbitrary Composio tools. This creates an indirect excessive permission risk, as the skill itself doesn't define the permissions but leverages a tool that could grant access to functionalities and data beyond the stated 'Cults automation' scope. If possible, restrict the capabilities of `RUBE_REMOTE_WORKBENCH` to only the necessary 'Cults' toolkit operations. Alternatively, provide clearer guidance or warnings about the broad access this tool might enable, and ensure the `rube` MCP is configured with the principle of least privilege.	Static	SKILL.md:67

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/1e0df1b6cf0e1f07.svg)](https://skillshield.io/report/1e0df1b6cf0e1f07)