Security Audit

browser-tool-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

browser-tool-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 Skill enables broad tool 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

85%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill enables broad tool execution via RUBE_REMOTE_WORKBENCH The skill documentation instructs the LLM to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This suggests the ability to execute arbitrary Composio tools, potentially beyond the explicit scope of 'Browser Tool Automation' as implied by the skill's name. If `run_composio_tool()` is not strictly limited to browser-related operations or if other powerful Composio tools (e.g., file system access, network requests) are available via Composio, this could grant the LLM excessive permissions, allowing it to perform actions unintended by the user or the skill's primary purpose. Clarify the scope of `run_composio_tool()` when used with `RUBE_REMOTE_WORKBENCH`. If it is intended to be limited to browser tools, explicitly state this in the documentation. If it can execute any Composio tool, document the full implications and advise host LLM developers to implement strict access controls and user consent mechanisms when this tool is invoked. Consider if `RUBE_REMOTE_WORKBENCH` should be exposed in a skill primarily focused on browser automation, or if a more granular tool for bulk browser operations would be safer.	LLM	SKILL.md:70

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/75083c318838ea0f.svg)](https://skillshield.io/report/75083c318838ea0f)