Security Audit

whautomate-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

CAUTION

Scanned 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

whautomate-automation received a trust score of 70/100, 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 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

70%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Potential Arbitrary Code Execution via Rube Remote Workbench The skill's documentation instructs the LLM to use `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' via `run_composio_tool()`. If `RUBE_REMOTE_WORKBENCH` provides an environment for arbitrary code execution (e.g., Python, shell commands), then the skill effectively grants the LLM the ability to execute arbitrary code through the `rube` MCP. This capability, if not properly sandboxed, could lead to command injection, data exfiltration, or system compromise if the LLM is prompted maliciously. The manifest's `requires: {"mcp": ["rube"]}` grants access to this potentially powerful tool. Clarify the exact capabilities and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure the underlying `rube` MCP environment for `RUBE_REMOTE_WORKBENCH` is strictly sandboxed to prevent arbitrary code execution, filesystem access, or network calls to untrusted destinations. If arbitrary code execution is an intended feature, clearly document the security implications and provide strong warnings, and consider if this level of access is truly necessary for the skill's purpose.	Static	SKILL.md:70

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/061595cb8de3cfaf.svg)](https://skillshield.io/report/061595cb8de3cfaf)