Security Audit

centralstationcrm-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

centralstationcrm-automation received a trust score of 82/100, 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 untrusted/unverified external MCP and toolkit provider, Potential for excessive permissions via generic tool execution.

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

78%

Behavioral Risk Signals

Network Access

2 findings

Filesystem Write

1 finding

Shell Execution

2 findings

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Reliance on untrusted/unverified external MCP and toolkit provider The skill explicitly instructs the user to connect to an external MCP server at `https://rube.app/mcp` and relies on toolkits provided by `composio.dev`. The security of this skill is entirely dependent on the integrity and trustworthiness of these external services. A compromise of `rube.app` or `composio.dev` could lead to arbitrary code execution, data exfiltration, or credential harvesting via the described tool interactions (e.g., `RUBE_MANAGE_CONNECTIONS` auth link, `RUBE_MULTI_EXECUTE_TOOL`). Verify the security posture and reputation of `rube.app` and `composio.dev`. Implement strict access controls and monitoring for any interactions with these external services. Consider sandboxing the execution environment for tools obtained from external MCPs.	LLM	SKILL.md:13
MEDIUM	Potential for excessive permissions via generic tool execution The skill describes using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This implies a generic mechanism to execute any tool available within the Composio ecosystem. If the Composio platform offers tools with broad system access (e.g., file system, network, shell commands), this could allow the agent to perform actions with excessive permissions, potentially leading to unintended data access, modification, or system compromise, beyond the scope of Centralstationcrm. Clarify and restrict the scope of tools executable via `RUBE_REMOTE_WORKBENCH` within the agent's environment. Ensure that `run_composio_tool()` is only permitted to execute tools with the minimum necessary privileges for the intended task. Implement a whitelist of allowed tools or capabilities if possible.	LLM	SKILL.md:69

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/b94e0ce937a11eba.svg)](https://skillshield.io/report/b94e0ce937a11eba)