Security Audit

bonsai-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

bonsai-automation received a trust score of 83/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include RUBE_REMOTE_WORKBENCH grants broad, undefined capabilities, Unversioned external MCP dependency introduces supply chain risk.

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

78%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	RUBE_REMOTE_WORKBENCH grants broad, undefined capabilities The `RUBE_REMOTE_WORKBENCH` tool, particularly with its `run_composio_tool()` function, is described for 'Bulk ops'. The term 'workbench' and the generic `run_composio_tool()` suggest a powerful, potentially unconstrained execution environment. If `run_composio_tool()` allows arbitrary code execution or shell commands, it presents a significant command injection vulnerability. Even if restricted to Composio tools, the lack of specific limitations implies excessive permissions, allowing the LLM to perform a wide range of actions without clear boundaries, potentially leading to unauthorized data access or modification. Clearly define and restrict the capabilities of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Specify what types of operations are allowed, what resources can be accessed, and whether arbitrary code execution is possible. Provide examples of safe usage and explicitly state any limitations on code execution or resource access.	LLM	SKILL.md:60
MEDIUM	Unversioned external MCP dependency introduces supply chain risk The skill relies on the `rube` MCP from `https://rube.app/mcp`. Both the manifest (`'requires': {'mcp': ['rube']}`) and the documentation do not specify a version for this external service. This means the skill will always use the latest version provided by `rube.app`. A malicious update or compromise of `rube.app` could introduce vulnerabilities or backdoors into the tools used by the LLM without any mechanism for the skill to detect or prevent it, posing a supply chain risk. Implement version pinning or integrity checks for external MCP dependencies. If direct versioning is not supported by the MCP system, consider alternative methods to ensure the integrity and immutability of the external service being consumed.	LLM	SKILL.md:20

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/47ceab11d7badf61.svg)](https://skillshield.io/report/47ceab11d7badf61)