Security Audit

mails-so-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

mails-so-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, 0 high, 1 medium, and 0 low severity. Key findings include Generic Rube MCP tool execution allows excessive permissions.

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

93%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Generic Rube MCP tool execution allows excessive permissions The skill documentation describes how to use `RUBE_SEARCH_TOOLS` to discover tools and `RUBE_MULTI_EXECUTE_TOOL` to execute them. While the skill's stated purpose is 'Mails So automation', the described mechanism for tool discovery and execution is generic to Rube MCP. This means an agent using this skill could be prompted to discover and execute any tool available through Rube MCP, not just those related to Mails So. If Rube MCP provides tools with broader permissions (e.g., filesystem access, network operations, or other sensitive SaaS integrations), this skill enables an agent to perform actions outside its intended scope, potentially leading to data exfiltration or unauthorized system access. Restrict the scope of `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL` calls within the skill to only Mails So specific tools. This could involve filtering `tool_slug` based on a predefined list of Mails So tools or ensuring that `RUBE_SEARCH_TOOLS` is always called with a `use_case` that strictly limits results to Mails So operations, and that the agent is instructed to only execute tools matching this scope. Alternatively, ensure the Rube MCP environment itself is configured to only expose Mails So tools to this skill.	LLM	SKILL.md:50

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/1cae37a249b4fde6.svg)](https://skillshield.io/report/1cae37a249b4fde6)