ClawHub

Verk Task Management

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Verk task-management client, with the main caveat that deleting tasks is immediate and should be used carefully.

Install this only if you trust Verk and can provide a scoped, revocable API key. Confirm exact task IDs before update or delete operations, and avoid setting VERK_API_URL unless you intentionally trust that alternate API server.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The README advertises destructive actions like `tasks delete <id>` and potentially high-impact actions like `flows trigger <id>` without any warning, confirmation guidance, or mention of least-privilege API key usage. In an agentic/natural-language context, this increases the chance that ambiguous prompts, prompt injection, or user misunderstanding could cause irreversible task deletion or unintended workflow execution.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly exposes a destructive `tasks delete <taskId>` operation but provides no guidance to require confirmation, verify intent, or warn the user before deletion. In an agent setting, this increases the risk of accidental or prompt-induced destructive actions that could remove work items without an easy recovery path.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The CLI exposes a destructive `tasks delete` operation that executes immediately with no confirmation prompt, dry-run mode, or safeguard against accidental invocation. In an agent skill context, where commands may be composed or triggered from natural-language requests, this raises the risk of unintended data loss from mis-parsing, prompt injection, or simple operator error.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal