Security Audit

magnetic-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

magnetic-automation received a trust score of 82/100, 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 Broad Tool Execution via RUBE_REMOTE_WORKBENCH, Unpinned External MCP Dependency.

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

78%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

2 findings

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad Tool Execution via RUBE_REMOTE_WORKBENCH The skill exposes `RUBE_REMOTE_WORKBENCH` which, according to the 'Quick Reference' table, can be used for 'Bulk ops' with `run_composio_tool()`. This function allows the execution of arbitrary Composio tools, not just those related to 'Magnetic operations' as implied by the skill's name and description. This grants the agent overly broad permissions, enabling it to potentially interact with other toolkits or perform actions outside the intended scope of this specific skill. Restrict the functionality of `RUBE_REMOTE_WORKBENCH` to only allow Magnetic-specific operations, or clearly document that this skill provides access to a broader range of Composio tools. If the intent is solely Magnetic automation, consider removing or limiting the `RUBE_REMOTE_WORKBENCH` tool from this skill's exposed capabilities.	LLM	SKILL.md:80
MEDIUM	Unpinned External MCP Dependency The skill relies on an external Rube MCP server (`https://rube.app/mcp`) for tool discovery and execution. There is no mechanism to pin the version or content served by this external endpoint. A compromise of the `rube.app` service could lead to the injection of malicious tool schemas or execution logic, posing a supply chain risk to agents using this skill. Implement mechanisms to verify the integrity and authenticity of the Rube MCP server's responses (e.g., cryptographic signatures, content hashing). Consider pinning to specific versions or content hashes of tool schemas if the Rube MCP supports such features, or host a trusted proxy for the MCP.	LLM	SKILL.md:15

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/f32df405cdc29f7f.svg)](https://skillshield.io/report/f32df405cdc29f7f)