Security Audit

dotsimple-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

dotsimple-automation received a trust score of 74/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Excessive Permissions via Dynamic Tool Execution, Vague but Potentially Overly Permissive '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

100%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

2 findings

Dynamic Code

2 findings

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Excessive Permissions via Dynamic Tool Execution The skill grants the LLM access to `RUBE_MULTI_EXECUTE_TOOL`, which allows the LLM to execute any tool discovered via `RUBE_SEARCH_TOOLS` with dynamically constructed arguments. This capability means that if the Composio ecosystem contains tools for sensitive operations (e.g., file system access, network requests, shell commands), a maliciously prompted LLM could discover and execute these tools, leading to unauthorized data exfiltration, command injection, or other harmful actions. The skill itself does not contain the malicious code, but it provides the means for the LLM to perform such actions if instructed. Implement strict access controls and sandboxing for the Rube MCP tools. Ensure that the LLM's execution environment is isolated and that the capabilities of tools discoverable via `RUBE_SEARCH_TOOLS` are narrowly scoped. Consider requiring explicit user confirmation for sensitive operations or for any execution of tools that could have broad impact.	LLM	SKILL.md:50
HIGH	Vague but Potentially Overly Permissive 'RUBE_REMOTE_WORKBENCH' The skill mentions `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. The term 'workbench' often implies a highly permissive environment, and 'bulk ops' suggests the ability to perform multiple or complex operations. Without further details on the specific capabilities and limitations of `run_composio_tool()` within this workbench, there's a significant risk of excessive permissions. A maliciously prompted LLM could potentially leverage this tool for broad, unauthorized actions, including data exfiltration or command injection, if the underlying `run_composio_tool()` allows such operations. Provide clear documentation and strict sandboxing for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Define and enforce the exact scope of operations allowed within the workbench. If possible, restrict its use to a predefined set of safe operations or require explicit human approval for any execution. Ensure the LLM's access to this tool is carefully managed.	LLM	SKILL.md:78

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/a292b65a72472696.svg)](https://skillshield.io/report/a292b65a72472696)