Security Audit

SEMrush Automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

SEMrush Automation received a trust score of 86/100, 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 Hardcoded dependency on external Managed Code Platform (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 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

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Hardcoded dependency on external Managed Code Platform (MCP) The skill's manifest declares a dependency on 'rube' as a Managed Code Platform (MCP), and the setup instructions in SKILL.md explicitly point to `https://rube.app/mcp`. This means the skill's functionality or execution environment relies on code or services provided by `rube.app`. If `rube.app` were to be compromised or become malicious, it could introduce arbitrary code execution, data exfiltration, or other security vulnerabilities into the agent's environment when this skill is used. This constitutes a significant supply chain risk, as the integrity of the skill's execution is tied to an external, potentially untrusted, third-party service. Implement robust supply chain security measures, including thorough vetting of third-party platforms and services. Consider using dependency integrity checks and sandboxing mechanisms for external code. Skill developers should evaluate the trustworthiness and security posture of `rube.app` and explore alternative, more controlled dependency mechanisms if available.	LLM	SKILL.md:19

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/4bf4463befa42b25.svg)](https://skillshield.io/report/4bf4463befa42b25)