Sheetsu

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Sheetsu integration that uses Membrane for authentication and API access, with normal but meaningful risk around changing spreadsheet-backed data.

Install this only if you trust Membrane and the npm-distributed CLI. Use a least-privileged Membrane/Sheetsu account where possible, prefer discovered Membrane actions over raw proxy requests, and explicitly review any operation that creates, updates, or deletes spreadsheet records.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill explicitly documents direct proxy requests and supports destructive HTTP methods such as POST, PUT, PATCH, and DELETE without requiring confirmation or warning about data modification risk. In an agent setting, this increases the chance of unintended record changes or deletion, especially if the model follows high-level user requests ambiguously or uses raw requests when safer predefined actions exist.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal