Security Audit

browserhub-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

browserhub-automation received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Skill exposes 'RUBE_REMOTE_WORKBENCH' tool with potential for broad execution.

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

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill exposes 'RUBE_REMOTE_WORKBENCH' tool with potential for broad execution The skill instructs the LLM to use the 'RUBE_REMOTE_WORKBENCH' tool for 'Bulk ops'. The term 'workbench' commonly implies an environment capable of executing arbitrary code or commands. If 'RUBE_REMOTE_WORKBENCH' allows general code execution, shell commands, or access to the underlying system beyond strictly sandboxed operations (e.g., `run_composio_tool()` as a restricted wrapper), an attacker could potentially prompt the LLM to leverage this tool for command injection, data exfiltration, or other malicious activities. By exposing this powerful tool, the skill grants the agent access to a capability that could be misused if the underlying tool is not sufficiently sandboxed. Clarify the exact capabilities and limitations of the `RUBE_REMOTE_WORKBENCH` tool. If it allows arbitrary code execution or shell commands, consider if this level of access is truly necessary for the skill's intended purpose. If not, restrict its usage or provide a more limited, sandboxed tool. Ensure that any functions executed within the workbench (like `run_composio_tool()`) are strictly controlled and do not allow for arbitrary code injection or access to sensitive resources.	LLM	SKILL.md:78

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/93744dfab4153989.svg)](https://skillshield.io/report/93744dfab4153989)