Security Audit

highlevel-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

highlevel-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 Access to Third-Party Platform APIs.

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 Access to Third-Party Platform APIs The skill provides extensive access to Highlevel operations via Composio's Rube MCP. The documentation outlines a workflow that involves dynamic tool discovery (`RUBE_SEARCH_TOOLS`) and subsequent execution of any discovered tool (`RUBE_MULTI_EXECUTE_TOOL`). This design grants the AI agent broad permissions over the connected Highlevel account, allowing it to potentially interact with any Highlevel API exposed through the Composio toolkit. This significantly increases the attack surface if the agent's instructions are compromised, as a malicious prompt could leverage these capabilities to perform unauthorized actions within the Highlevel platform. Implement granular access controls or scope limitations within the Composio Highlevel toolkit configuration to restrict the types of operations the AI agent can perform. Ensure robust input validation and prompt injection defenses are in place for the LLM interacting with this skill to prevent misuse of its broad capabilities.	LLM	SKILL.md:35

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e4cc1dbf6059d348.svg)](https://skillshield.io/report/e4cc1dbf6059d348)