Security Audit

ravenseotools-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

ravenseotools-automation received a trust score of 86/100, 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 Excessive Permissions / 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

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Excessive Permissions / Potential Command Injection via RUBE_REMOTE_WORKBENCH The skill exposes `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'workbench' and 'bulk ops' strongly suggests a highly flexible and powerful execution environment, potentially allowing arbitrary code execution or complex scripting within the Rube MCP. If `run_composio_tool()` can interpret arbitrary input as code or commands, it presents a significant command injection vulnerability. Furthermore, such a powerful tool grants excessive permissions to the LLM, enabling it to perform actions beyond simple API calls, potentially leading to unauthorized data access, modification, or exfiltration if the underlying Rube environment or connected Ravenseotools account has broad permissions. Clarify the exact capabilities and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it allows arbitrary code execution, consider removing its exposure to the LLM or implementing strict input validation and sandboxing. If it's intended for specific, constrained 'bulk operations', ensure the interface only allows those specific operations and cannot be coerced into executing arbitrary commands or scripts. Provide a detailed schema for `RUBE_REMOTE_WORKBENCH` that explicitly defines its safe usage.	LLM	SKILL.md:67

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/92760b8578ac60ec.svg)](https://skillshield.io/report/92760b8578ac60ec)