ClawHub
Back to skill

Security audit

ClawSheet Wizard

Security checks for vulnerabilities and agentic risk

Overview

This spreadsheet skill is purpose-aligned and mostly read/report oriented, with no evidence of hidden persistence, exfiltration, or destructive behavior.

Install only if you are comfortable running local Python scripts on spreadsheets you choose. Review generated reports and keep backups before relying on any repaired or regenerated workbook, because the documentation advertises auto-fix behavior more strongly than the current code supports.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill advertises spreadsheet creation and editing capabilities, including commands that write modified workbooks, but the metadata declares no permissions. That mismatch can bypass user expectations and policy controls, increasing the risk of unauthorized file modification or unsafe agent behavior when the skill is invoked.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The documented commands include automatic repair and output generation that can change workbook contents, but the skill does not clearly warn users that it may alter spreadsheets. In a spreadsheet-editing context this is significant because silent formula fixes or workbook rewrites can corrupt business logic, overwrite important data, or produce unreviewed changes that users trust.

Static analysis

No suspicious patterns detected.