Security Audit

emaillistverify-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

CAUTION

Scanned 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

emaillistverify-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 Hardcoded, Unverified External Dependency (Rube MCP), Vague and Potentially Overly Permissive '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

70%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

2 findings

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Hardcoded, Unverified External Dependency (Rube MCP) The skill explicitly instructs the user/LLM to connect to a hardcoded external endpoint, `https://rube.app/mcp`, for its core functionality. This creates a significant supply chain risk. If the `rube.app` domain or the MCP server hosted there were compromised, an attacker could serve malicious tool schemas or execute arbitrary code via the Rube platform, directly impacting any agent using this skill. There is no mechanism described within the skill to verify the integrity or authenticity of the Rube MCP endpoint or the tools it provides. Implement a mechanism to verify the authenticity and integrity of the Rube MCP endpoint and the tools it provides (e.g., cryptographic signatures, trusted registry). Avoid hardcoding critical external service URLs without robust verification. Consider allowing configuration of the MCP endpoint with appropriate security warnings.	Static	SKILL.md:19
HIGH	Vague and Potentially Overly Permissive 'RUBE_REMOTE_WORKBENCH' The skill mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The description of this capability is extremely vague, implying a powerful, generic execution environment. If `run_composio_tool()` allows arbitrary code execution, script injection, or highly privileged operations on the Rube platform, and an LLM can be prompted to pass malicious arguments to it, this could lead to severe command injection or excessive permissions. The lack of detail makes it impossible to assess the security boundaries of this function, posing a significant risk. Provide clear and detailed documentation on the exact capabilities, security model, and input validation of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that `run_composio_tool()` operates with the principle of least privilege and has robust input sanitization to prevent command injection or unintended operations. If it allows arbitrary code, this should be explicitly stated and heavily restricted.	Static	SKILL.md:59

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/34bdb512fa29781e.svg)](https://skillshield.io/report/34bdb512fa29781e)