Security Audit

modelry-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

modelry-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 2 findings: 0 critical, 0 high, 1 medium, and 1 low severity. Key findings include Unpinned MCP dependency, Broad tool execution capability via RUBE_MULTI_EXECUTE_TOOL.

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

91%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings2

Severity	Finding	Layer	Location
MEDIUM	Unpinned MCP dependency The skill's manifest requires the 'rube' MCP without specifying a version. This can lead to unexpected behavior or security vulnerabilities if the 'rube' MCP updates with breaking changes or introduces malicious code, as the skill would automatically use the latest version without explicit review. Pin the 'rube' MCP dependency to a specific, known-good version or version range in the manifest to ensure stability and security.	LLM	SKILL.md
LOW	Broad tool execution capability via RUBE_MULTI_EXECUTE_TOOL The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` with tool slugs discovered dynamically via `RUBE_SEARCH_TOOLS`. This grants the LLM broad capability to execute any operation exposed by the `modelry` toolkit. While the skill advises dynamic discovery and schema compliance, an LLM's interpretation of user intent could lead to unintended or malicious tool invocations if the underlying tools have sensitive or destructive capabilities. Implement stricter access controls or allow-lists for specific tool slugs that the LLM is permitted to execute, rather than allowing execution of any discovered tool. Ensure the `modelry` toolkit itself follows the principle of least privilege.	LLM	SKILL.md:45

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/08235509f18ef47e.svg)](https://skillshield.io/report/08235509f18ef47e)