Security Audit

route4me-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

route4me-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 Broad Tool Access, Arbitrary Composio Tool Execution via 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

Shell Execution

2 findings

Dynamic Code

1 finding

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Excessive Permissions via Broad Tool Access The skill grants the LLM access to powerful Rube MCP tools (`RUBE_MULTI_EXECUTE_TOOL`, `RUBE_REMOTE_WORKBENCH`) which allow dynamic discovery and execution of a wide range of operations on the Route4me platform via Composio. This broad access means the LLM can perform virtually any action supported by the Route4me API through the Composio toolkit, potentially including sensitive data manipulation, deletion, or exposure, without fine-grained constraints defined within the skill itself. The instruction to 'Always search tools first' further emphasizes this dynamic and unconstrained execution capability. Implement stricter access controls at the Rube MCP or Composio toolkit level to limit the scope of actions an LLM can take. If possible, define a more granular set of specific Route4me operations that the skill is intended to perform, rather than allowing dynamic discovery and execution of all available tools. Require explicit user confirmation for sensitive or destructive operations.	LLM	SKILL.md:57
HIGH	Arbitrary Composio Tool Execution via Remote Workbench The skill mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This suggests the capability to execute arbitrary Composio tools, not just those specific to Route4me. This is an extremely powerful and broad permission that could allow the LLM to interact with any service or perform any action supported by the Composio platform, potentially leading to unintended consequences or misuse if not properly constrained. Review the capabilities of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If this allows execution of tools beyond the intended scope (e.g., other toolkits), consider restricting its availability or functionality within the skill's context. Ensure that any use of this tool requires explicit, fine-grained permissions and user consent for each operation.	LLM	SKILL.md:84

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/9ffca9dada7be626.svg)](https://skillshield.io/report/9ffca9dada7be626)