Security Audit

google-admin-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

google-admin-automation received a trust score of 81/100, 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 Skill grants excessive Google Workspace admin permissions, Skill enables broad data retrieval of Google Workspace user/group data.

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

Dynamic Code

1 finding

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Skill grants excessive Google Workspace admin permissions The skill provides access to a wide range of highly privileged Google Workspace administrative tools, including `GOOGLE_ADMIN_CREATE_USER`, `GOOGLE_ADMIN_DELETE_USER`, `GOOGLE_ADMIN_SUSPEND_USER`, `GOOGLE_ADMIN_ADD_USER_TO_GROUP`, and `GOOGLE_ADMIN_CREATE_GROUP`. These tools require and operate with full Google Workspace admin privileges, allowing for critical and potentially irreversible actions across the entire domain. An LLM using this skill could, if compromised or misused, perform destructive actions or widespread changes, such as permanently deleting user accounts. Implement granular access controls for the underlying Google Admin API. Ensure the LLM's execution environment and prompts are robustly secured against misuse. Consider breaking down the skill into more narrowly scoped sub-skills if possible, or requiring explicit human approval for highly destructive actions.	LLM	SKILL.md:100
MEDIUM	Skill enables broad data retrieval of Google Workspace user/group data The skill exposes tools such as `GOOGLE_ADMIN_LIST_USERS`, `GOOGLE_ADMIN_LIST_GROUPS`, `GOOGLE_ADMIN_GET_USER`, and `GOOGLE_ADMIN_LIST_GROUP_MEMBERS`. These tools, when used with the required admin privileges, can retrieve extensive sensitive information about an organization's users (e.g., emails, names, suspension status) and group structures. If an LLM is compromised or maliciously prompted, it could use these capabilities to exfiltrate a significant amount of internal organizational data. Implement strict output filtering and monitoring for LLM responses when using data retrieval tools. Ensure LLM prompts are designed to prevent unauthorized data disclosure. Consider masking sensitive fields or requiring explicit user confirmation for data export actions.	LLM	SKILL.md:30

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/967252a02873d593.svg)](https://skillshield.io/report/967252a02873d593)