Security Audit

rosette-text-analytics-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

rosette-text-analytics-automation received a trust score of 86/100, 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 Broad Tool Execution Scope via Rube 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 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

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad Tool Execution Scope via Rube MCP The skill's documentation instructs the LLM to use `RUBE_SEARCH_TOOLS` for tool discovery and `RUBE_MULTI_EXECUTE_TOOL` for execution. While the skill's stated purpose is Rosette Text Analytics, the underlying Rube MCP mechanism grants a broad capability to discover and execute tools from any connected toolkit, not just Rosette. This means an LLM using this skill could potentially be prompted to interact with other, unintended toolkits if they are available via Rube MCP and the LLM's internal reasoning is not sufficiently constrained to the Rosette Text Analytics domain. This broad access could lead to unintended actions or data exposure if not properly managed by the LLM or the Rube MCP system. Implement stricter scope control within the Rube MCP system to allow skills to declare and enforce limitations on which toolkits or tool slugs can be executed (e.g., restrict `RUBE_MULTI_EXECUTE_TOOL` to only `rosette_text_analytics` tools for this skill). Alternatively, the skill documentation should explicitly warn about the broad execution capabilities and instruct the LLM to strictly adhere to the intended toolkit (Rosette Text Analytics) when using `RUBE_MULTI_EXECUTE_TOOL`.	LLM	SKILL.md:55

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e99db4606918bcd3.svg)](https://skillshield.io/report/e99db4606918bcd3)