Security Audit

splitwise-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

splitwise-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 Potential Command Injection 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

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via RUBE_REMOTE_WORKBENCH The skill suggests using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. `RUBE_REMOTE_WORKBENCH` implies an environment capable of executing arbitrary code or tools. If `run_composio_tool()` can be invoked with arbitrary arguments or tool names without strict validation, sandboxing, or an allow-list, it could lead to command injection or the execution of unintended, potentially malicious operations within the remote workbench environment. The skill provides no examples or safety guidelines for its use, increasing the risk of misuse by an LLM agent. Provide clear examples and strict guidelines for using `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure the underlying `run_composio_tool()` function is properly sandboxed, validates all inputs, and restricts execution to an explicit allow-list of safe operations. If possible, avoid exposing such a powerful, unconstrained execution mechanism to an LLM agent without robust guardrails.	LLM	SKILL.md:67

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/59dbda60ce54ebb3.svg)](https://skillshield.io/report/59dbda60ce54ebb3)