Security Audit

msg91-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

msg91-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, 1 high, 0 medium, and 0 low severity. Key findings include Broad tool execution capabilities via Rube MCP.

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

85%

Behavioral Risk Signals

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad tool execution capabilities via Rube MCP The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` which allow for the execution of arbitrary tools exposed by the Rube MCP. While the skill's stated purpose is Msg91 automation, these functions are not explicitly scoped to Msg91-specific tools within the skill's definition. This grants the LLM excessive permissions, potentially allowing it to perform actions beyond the intended scope, including interacting with other services or performing unintended operations if the Rube MCP exposes a wider range of tools. Specifically, `RUBE_MULTI_EXECUTE_TOOL` can execute any `TOOL_SLUG_FROM_SEARCH`, and `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` implies generic Composio tool execution. Restrict the scope of tools that can be executed by `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to only Msg91-specific tools. This could involve modifying the skill to only call specific, pre-approved Msg91 tool slugs, or ensuring the `rube` MCP itself provides fine-grained access control that can be enforced by the skill's configuration.	LLM	SKILL.md:50

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/c9e442b6f525c051.svg)](https://skillshield.io/report/c9e442b6f525c051)