ClawHub
Back to skill

Security audit

IceCube Tasks

Security checks across malware telemetry and agentic risk

Overview

This skill is a file-backed task tracker, and its local persistence behavior is disclosed and aligned with that purpose.

Install this if you want agents to keep a durable local task ledger. Be aware it may create or update files in state/tasks during task-management conversations, so ask your agent to confirm before making persistent task changes if that matters for your workspace.

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
89% confidence
Finding
The description includes broad trigger phrases such as 'task management', 'to-do list', and 'project management', which can cause the skill to activate in many ordinary conversations. Because this skill then instructs persistent file writes in the workspace, accidental invocation can lead to unintended state changes and file creation outside clear user intent.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly directs the agent to write, update, and move files under `state/tasks/` but does not require verifying that the user wants persistent workspace modifications. In an agent setting, this creates a real risk of unauthorized or surprising file-system changes, especially if the skill is auto-invoked or used in repositories where `state/` may be tracked, synced, or consumed by other automation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.