Security Audit

polygon-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

polygon-automation received a trust score of 73/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Potential Arbitrary Code Execution via RUBE_REMOTE_WORKBENCH.

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

70%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Potential Arbitrary Code Execution via RUBE_REMOTE_WORKBENCH The skill documentation references `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The naming convention ('workbench', 'run_tool') strongly suggests that this tool allows for the execution of arbitrary code or scripts within the Rube MCP environment. If the Rube MCP environment is not rigorously sandboxed and isolated, or if `run_composio_tool()` can be invoked with untrusted inputs, this presents a critical command injection vulnerability. An attacker could potentially leverage this to execute arbitrary commands on the host system or within the Rube MCP's network context, leading to data compromise, system takeover, or further lateral movement. Immediately clarify the exact capabilities and security model of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it enables arbitrary code execution, ensure it operates within a highly restricted, isolated, and ephemeral sandbox environment with minimal necessary permissions. Implement strict input validation and sanitization for any arguments passed to `run_composio_tool()`. Provide explicit warnings about the security implications of using this tool and consider if such a powerful, potentially unconstrained execution capability should be directly exposed to an LLM agent without robust guardrails and human-in-the-loop verification.	LLM	SKILL.md:69

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/5fe5103cf5268866.svg)](https://skillshield.io/report/5fe5103cf5268866)