Security Audit

sms-alert-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

sms-alert-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 and Connection Management 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

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad Tool Execution and Connection Management via Rube MCP The skill integrates with Rube MCP, exposing powerful generic tools like `RUBE_MULTI_EXECUTE_TOOL`, `RUBE_REMOTE_WORKBENCH` (with `run_composio_tool()`), and `RUBE_MANAGE_CONNECTIONS`. While the documentation guides the LLM to use these for 'SMS Alert operations' and advises searching for tools first, these underlying tools are generic. An attacker could potentially manipulate the LLM (e.g., via prompt injection) to bypass the intended 'SMS Alert' scope, leading to unauthorized execution of other Rube-managed tools or management of connections for other sensitive toolkits, thereby granting excessive permissions beyond the skill's stated purpose. Implement strict access control policies within the Rube MCP environment to limit the toolkits and operations an agent can access, even if it attempts to call generic execution tools. Ensure the LLM's prompt engineering strongly enforces the 'SMS Alert' scope and prevents deviation. Consider using more granular, purpose-built tools if available, rather than relying solely on generic execution wrappers for sensitive operations.	LLM	SKILL.md:61

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/15d91d77d9074e30.svg)](https://skillshield.io/report/15d91d77d9074e30)