Security Audit

zoominfo-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

zoominfo-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, 2 medium, and 0 low severity. Key findings include Broad tool execution via generic Rube MCP tools, Unpinned dependency on 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 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

86%

Behavioral Risk Signals

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
MEDIUM	Broad tool execution via generic Rube MCP tools The skill exposes generic Rube MCP tools like `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. While the skill's stated purpose is Zoominfo automation, these tools, especially when combined with `RUBE_SEARCH_TOOLS`, could potentially allow the LLM to discover and execute tools beyond the intended Zoominfo scope if the Rube MCP is configured to expose other toolkits. `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` suggests a powerful, potentially arbitrary execution capability on the remote platform. Restrict the Rube MCP integration to explicitly only allow Zoominfo-related toolkits and operations. Implement strict access controls and scope limitations on the Rube MCP side for this skill's usage. If `RUBE_REMOTE_WORKBENCH` allows arbitrary code, consider if this is truly necessary and if it can be further constrained.	LLM	SKILL.md:59
MEDIUM	Unpinned dependency on Rube MCP The skill's manifest specifies a dependency on the `rube` MCP without a specific version constraint. This means the skill could interact with any version of the Rube MCP, potentially leading to unexpected behavior, compatibility issues, or security vulnerabilities if future versions introduce breaking changes or known exploits. Specify a minimum or exact version for the `rube` MCP dependency in the skill's manifest to ensure predictable and secure interactions.	LLM	SKILL.md

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/4f3954aef6f4c49a.svg)](https://skillshield.io/report/4f3954aef6f4c49a)