Security Audit
Excel Automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
Excel Automation received a trust score of 88/100, 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 Spreadsheet and Cloud Storage Access.
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
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Broad Spreadsheet and Cloud Storage Access The skill provides access to powerful tools for manipulating spreadsheets and cloud storage resources. Specifically, `EXCEL_CREATE_WORKBOOK` can create new workbooks in OneDrive, and `GOOGLESHEETS_CREATE_GOOGLE_SHEET1` can create new Google Sheets in Drive. Tools like `GOOGLESHEETS_BATCH_UPDATE`, `GOOGLESHEETS_UPSERT_ROWS` (for writing/updating data), and `GOOGLESHEETS_BATCH_GET` (for reading data) grant extensive capabilities. If the underlying Rube MCP integration is configured with broad OAuth scopes (e.g., full Drive or Spreadsheet access), a compromised or misconfigured agent could be instructed to exfiltrate sensitive data, tamper with critical spreadsheets, or create a large number of unwanted files, leading to data loss, corruption, or resource abuse. Ensure that the Rube MCP integration for Excel and Google Sheets uses the principle of least privilege, requesting only the necessary OAuth scopes. Implement strict access controls and monitoring for agent actions involving these powerful tools. Consider granular permissions for specific spreadsheet IDs or folders if possible to limit the blast radius of potential misuse. | LLM | SKILL.md:160 |
Scan History
Embed Code
[](https://skillshield.io/report/77d5a8d44da7e464)
Powered by SkillShield