Security Audit

alpha-vantage-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

CAUTION

Scanned 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

alpha-vantage-automation received a trust score of 70/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Excessive Permissions via Generic Workbench Tool, Hardcoded Dependency on External 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 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

70%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

2 findings

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Excessive Permissions via Generic Workbench Tool The skill exposes `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. A 'workbench' tool typically implies a broad execution environment, and `run_composio_tool()` suggests the ability to execute arbitrary Composio tools. If the underlying Composio platform or the tools it exposes have access to resources beyond the intended scope (e.g., filesystem, network access to arbitrary domains, or other connected services), an attacker who gains control of the LLM agent could leverage this generic execution capability to perform unauthorized actions or access sensitive data not directly related to Alpha Vantage operations. Restrict the capabilities of `RUBE_REMOTE_WORKBENCH` to only allow specific, pre-approved operations relevant to Alpha Vantage, or ensure that `run_composio_tool()` is sandboxed and cannot access sensitive resources or execute arbitrary code. Provide a more granular tool for bulk operations if possible, rather than a generic workbench.	Static	SKILL.md:64
HIGH	Hardcoded Dependency on External MCP Service The skill has a hardcoded dependency on an external Managed Control Plane (MCP) service at `https://rube.app/mcp`. The manifest explicitly requires `mcp: ['rube']` and the documentation instructs users to add this specific endpoint. This introduces a supply chain risk: if the `rube.app` service is compromised, becomes malicious, or is taken over, the LLM agent's interactions with Alpha Vantage (and potentially other services managed by Rube MCP) could be intercepted, manipulated, or redirected. The documentation also states 'No API keys needed — just add the endpoint and it works' for the MCP itself, which could be a risk if the endpoint's security relies solely on trust without explicit authentication for the MCP connection. Implement mechanisms to verify the integrity and authenticity of the external MCP service. Consider allowing users to configure their own trusted MCP endpoints or providing alternative, self-hosted options. Clearly document the security implications of relying on a third-party MCP service. If possible, implement cryptographic verification of tool schemas or execution plans received from the MCP.	Static	SKILL.md:16

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/feca4523a68c3c36.svg)](https://skillshield.io/report/feca4523a68c3c36)