Google Tasks

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Google Tasks integration that uses Membrane to read and change task data, with no evidence of hidden or unrelated behavior.

Install only if you are comfortable using Membrane as the gateway to your Google Tasks account. Review the OAuth consent screen, use the intended Google account, and ask the agent to confirm the exact task or task list before deleting items, clearing completed tasks, moving tasks, or using raw proxy requests.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The skill description is broad enough to trigger on many ordinary requests involving tasks, records, or workflow automation, which can cause over-invocation of this integration. In a skill with write and delete capabilities against a live Google Tasks account, overly broad routing increases the chance that the agent selects this skill when the user did not clearly intend external side effects.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation prominently exposes destructive actions like deleting tasks, deleting task lists, and clearing completed tasks without instructing the agent to obtain explicit confirmation first. In an agent setting, that omission can lead to accidental irreversible data loss if the model infers user intent too aggressively or executes a mistaken action selection.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal