Security Audit

rocketlane-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

rocketlane-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 Broad Tool Execution Capabilities, Dynamic External Dependency with No Version Pinning.

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 20, 2026 (commit 27904475). 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

Network Access

1 finding

Shell Execution

2 findings

Dynamic Code

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad Tool Execution Capabilities The skill instructs the agent to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` which provide broad capabilities to execute various tools and potentially arbitrary code (via `run_composio_tool()`). This grants significant control over integrated services (Rocketlane) and could be exploited by a malicious prompt to perform unauthorized operations. Implement stricter access controls or approval mechanisms for sensitive operations performed via `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH`. Ensure the agent's environment has robust guardrails against malicious tool usage.	LLM	SKILL.md:59
HIGH	Dynamic External Dependency with No Version Pinning The skill relies on dynamically fetched tool schemas and execution capabilities from `https://rube.app/mcp` via `RUBE_SEARCH_TOOLS`. There is no version pinning or integrity checking for these external dependencies. A compromise of the `rube.app/mcp` endpoint could lead to the injection and execution of malicious tool definitions by the agent, posing a significant supply chain risk. Implement mechanisms to verify the integrity and authenticity of tool schemas fetched from external sources. Consider pinning to specific versions or hashes of tool definitions where possible, or at least implementing robust monitoring for changes in the external MCP.	LLM	SKILL.md:28

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/6aa9cb2f4cbb5bb6.svg)](https://skillshield.io/report/6aa9cb2f4cbb5bb6)