Trust Assessment
google-sheets received a trust score of 87/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Unpinned npm dependency version, Broad credential search path, Broad Google Sheets API permissions.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Unpinned npm dependency version Dependency 'googleapis' is not pinned to an exact version ('^140.0.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/longmaba/google-sheet/package.json | |
| MEDIUM | Broad Google Sheets API permissions The skill requests and utilizes the `https://www.googleapis.com/auth/spreadsheets` OAuth scope, granting full read/write access to all spreadsheets the service account can access. This includes creating, deleting, modifying content, and managing sheet properties. If an attacker gains control over the arguments passed to the skill (e.g., `spreadsheetId`, `range`, `data`, `formatJson`), they could perform extensive malicious operations on any accessible Google Sheet, such as data exfiltration, data corruption, or injecting malicious formulas/scripts into cells. Implement stricter input validation and sanitization for all command-line arguments, especially those that directly manipulate spreadsheet content (e.g., `data`, `formatJson`). Consider if a narrower scope (e.g., read-only or specific sheet access) could fulfill some use cases, or if user confirmation is needed for destructive operations. Ensure the LLM calling the skill is robust against generating malicious inputs. | LLM | scripts/sheets.js:49 | |
| INFO | Broad credential search path The skill searches for Google service account credentials in multiple locations, including environment variables, the current working directory (`service-account.json`, `credentials.json`), and a user's home directory (`~/.config/google-sheets/credentials.json`). While intended for legitimate setup, this broad search path makes credentials easily discoverable by a malicious actor if the skill's execution environment is compromised. The scope of the credentials is limited to Google Sheets, which reduces the overall impact. Consider restricting credential search paths to only environment variables or a single, well-secured location. Ensure the skill's runtime environment is isolated and that credential files have appropriate file system permissions. | LLM | scripts/sheets.js:19 |
Scan History
Embed Code
[](https://skillshield.io/report/b70f2cf20d713c1b)
Powered by SkillShield