Security Audit

openrouter-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned 6 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

openrouter-automation received a trust score of 95/100, 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, 0 high, 1 medium, and 0 low severity. Key findings include Potential for Excessive Permissions 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

93%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Potential for Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill instructs the use of `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. The term 'workbench' and 'bulk ops' often imply a broad execution environment, potentially allowing for arbitrary code execution, file system access, or other sensitive system interactions if the underlying `run_composio_tool()` is not sufficiently sandboxed or restricted. This could lead to excessive permissions, allowing the agent to perform actions beyond the intended scope of Openrouter automation. While the specific capabilities of `run_composio_tool()` are not defined within this skill, its inclusion as a core operation suggests a powerful, potentially unconstrained interface that could be exploited if the Rube MCP implementation is not secure. Clarify the exact scope and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` in the skill documentation. Ensure that the Rube MCP strictly sandboxes and limits the capabilities of `run_composio_tool()` to only what is necessary for Openrouter automation, preventing arbitrary code execution or access to unintended resources. If possible, consider if more specific, less powerful tools can achieve the desired functionality instead of a general 'workbench' tool.	LLM	SKILL.md:80

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e47a3612afe9f365.svg)](https://skillshield.io/report/e47a3612afe9f365)