ClawHub

topydo

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward topydo/todo.txt command guide with normal local task-management risks but no evidence of hidden or malicious behavior.

Install topydo only from a trusted package source, and treat commands that delete, archive, edit, sort, or bulk-complete tasks as data-changing actions. Preview matching tasks first and confirm the exact task IDs or filters before allowing the agent to run destructive commands.

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
91% confidence
Finding
The skill description includes very broad activation cues such as 'use for any task management, todo lists, or when the user mentions tasks, todos, or todo.txt,' which can cause the agent to invoke this skill in many loosely related contexts. Over-broad triggering increases the chance of unintended execution of task-management commands, including state-changing operations, on user data without sufficiently explicit intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents destructive deletion commands, including bulk deletion by expression, without warning the operator to confirm scope or preview affected tasks. In an agent setting, this creates a realistic risk of accidental or overbroad data loss if a natural-language request is mapped to `topydo del` or `topydo del -e` without explicit user confirmation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal