Security Audit

hotspotsystem-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

hotspotsystem-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 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Broad operational scope granted via Rube MCP dependency, `RUBE_REMOTE_WORKBENCH` suggests potential for command injection.

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

Network Access

1 finding

Shell Execution

2 findings

Dynamic Code

2 findings

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad operational scope granted via Rube MCP dependency The skill's manifest declares a dependency on `mcp: ["rube"]`, and the `SKILL.md` details how to leverage Rube MCP for `RUBE_MANAGE_CONNECTIONS`, `RUBE_SEARCH_TOOLS`, `RUBE_MULTI_EXECUTE_TOOL`, and `RUBE_REMOTE_WORKBENCH`. These tools, particularly `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`, grant the LLM broad capabilities to interact with external systems (Hotspotsystem) and execute arbitrary operations via discovered tools. This significantly increases the LLM's operational scope and attack surface, making it vulnerable to misuse if the LLM is compromised via prompt injection or other means. While necessary for the skill's intended function, this broad access poses a security risk. Ensure Rube MCP and its connectors are robustly secured, sandboxed, and operate with the principle of least privilege. Implement strict access controls, input validation, and comprehensive monitoring for all tool executions. The LLM's use of such powerful tools should be carefully constrained and audited.	Static	SKILL.md:1
HIGH	`RUBE_REMOTE_WORKBENCH` suggests potential for command injection The skill's 'Quick Reference' section mentions `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. The term 'workbench' typically implies an environment where code or commands can be executed. If the underlying `run_composio_tool()` function within `RUBE_REMOTE_WORKBENCH` allows for arbitrary code execution or shell command invocation without sufficient sandboxing and input validation, a malicious prompt could instruct the LLM to use this function to execute harmful commands, leading to command injection. Clarify the exact capabilities and security model of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Implement robust sandboxing, strict input validation, and least privilege principles to prevent arbitrary code execution. Ensure that any code executed within the workbench environment is isolated and cannot impact the host system or other sensitive resources.	Static	SKILL.md:60

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/b003de3a54da66c7.svg)](https://skillshield.io/report/b003de3a54da66c7)