Security Audit

mapbox-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

mapbox-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 Vague `RUBE_REMOTE_WORKBENCH` tool suggests excessive permissions and potential for arbitrary code execution.

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

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Vague `RUBE_REMOTE_WORKBENCH` tool suggests excessive permissions and potential for arbitrary code execution The skill documentation mentions `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' using `run_composio_tool()`. The term 'workbench' and the generic `run_composio_tool()` function suggest a highly flexible and potentially unconstrained execution environment. If `run_composio_tool()` allows the execution of arbitrary code or commands, or if the 'tools' it can run are not strictly validated and sandboxed, this could lead to arbitrary command injection, data exfiltration, or other malicious activities. The documentation provides no details on the security model or limitations of this tool, making its capabilities and potential risks unclear. Clarify the exact capabilities and security model of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that `run_composio_tool()` is strictly sandboxed, only allows execution of pre-approved and validated tools, and does not permit arbitrary code or shell command execution. If it is intended for arbitrary scripting, this should be explicitly stated with strong warnings and clear isolation mechanisms.	LLM	SKILL.md:69

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/f37950f734880e7e.svg)](https://skillshield.io/report/f37950f734880e7e)