ClawHub
Back to skill

Security audit

Todo Skill

Security checks across malware telemetry and agentic risk

Overview

This is a simple to-do planning skill whose code only manages an in-memory task list and does not show hidden access or unsafe behavior.

Reasonable to install for general planning and to-do tracking. Review any suggested step before letting an agent act on money, accounts, public posts, regulated work, or irreversible changes.

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 (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The invocation phrase is broad enough to match many ordinary planning requests, which can cause the skill to activate unexpectedly and influence conversations outside the user's specific intent. Overbroad triggering increases the chance of prompt-surface abuse, unintended workflow takeover, or execution of actions under the wrong context.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.