Security Audit

borneo-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

borneo-automation received a trust score of 85/100, 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 Dynamic Tool Discovery from Unversioned External MCP.

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

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Dynamic Tool Discovery from Unversioned External MCP The skill relies on an external, unversioned Rube MCP endpoint (`https://rube.app/mcp`) for its core functionality, as indicated by the manifest (`'requires': {'mcp': ['rube']}`) and the setup instructions. The skill explicitly instructs the LLM to dynamically discover tools via `RUBE_SEARCH_TOOLS` because 'Tool schemas change. Never hardcode tool slugs or arguments'. This dynamic discovery and execution of tools from an external, unversioned source introduces a significant supply chain risk. If the `rube.app` service were compromised or if its maintainers introduced malicious changes, the LLM could be instructed to discover and execute arbitrary, harmful operations via `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH` without explicit vetting or version control within the skill package. Implement version pinning for the Rube MCP endpoint or the specific toolkits it provides. If dynamic discovery is essential, introduce a robust vetting or sandboxing mechanism for newly discovered or updated tools. Require explicit user confirmation before executing tools that have changed or are newly discovered from an unversioned source. Consider mirroring or locally hosting critical tool schemas to reduce reliance on external, dynamic endpoints.	LLM	SKILL.md:15

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/0da2c3838d3a2742.svg)](https://skillshield.io/report/0da2c3838d3a2742)