ClawHub
Back to skill

Security audit

Task

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed task-management wrapper that forwards user task requests to a named Tasker tool, with no evidence of hidden data access or unrelated execution.

Install this if you trust the Tasker tool/plugin it dispatches to and want natural-language task management. Be aware that task-related phrasing may invoke the skill, and text after /task is passed through directly to tasker_cmd, so avoid sending sensitive content unless that downstream tool’s storage and handling are acceptable.

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
91% confidence
Finding
The skill description is broad enough to match ordinary task-related conversation, which increases the chance of unintended activation during normal chat. Because the skill can translate natural language directly into raw CLI arguments for a task-management tool, accidental routing could trigger state-changing operations such as adding or completing tasks without clear user intent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.