Security Audit

gosquared-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

gosquared-automation received a trust score of 76/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Unpinned Dynamic Tool Dependencies, Potentially Unconstrained Remote Workbench Access.

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

2 findings

Dynamic Code

2 findings

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Unpinned Dynamic Tool Dependencies The skill explicitly instructs to always use `RUBE_SEARCH_TOOLS` to discover current tool schemas and slugs, and warns against hardcoding. This means the skill relies on dynamically fetched, unversioned tools and schemas from Rube MCP. A malicious update or compromise of the Rube MCP service or the Gosquared toolkit could lead to the skill executing arbitrary or malicious code without explicit version control or pinning, posing a significant supply chain risk. Implement version pinning or content hashing for Rube MCP tools and schemas. Require explicit approval for tool updates or provide mechanisms to specify minimum/maximum allowed versions for dynamically discovered tools.	LLM	SKILL.md:59
HIGH	Potentially Unconstrained Remote Workbench Access The skill mentions `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' which can `run_composio_tool()`. The term 'workbench' suggests a broad execution environment. Without clear sandboxing or scope limitations defined for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`, this could grant excessive permissions, potentially allowing arbitrary code execution, command injection, or access to resources beyond the intended Gosquared operations. Clarify the exact capabilities and security boundaries of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure these tools are strictly sandboxed and only permit operations relevant to the Gosquared toolkit, preventing arbitrary code execution or access to sensitive system resources. If arbitrary code execution is intended, this should be explicitly stated with strong warnings and isolation mechanisms.	LLM	SKILL.md:74

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/49ac7f0f8abe4993.svg)](https://skillshield.io/report/49ac7f0f8abe4993)