ClawHub
Back to skill

Security audit

Waitspin

Security checks across malware telemetry and agentic risk

Overview

The skill is a disclosed WaitSpin helper for account setup, ads, wallet checks, and developer-tool earning-surface installs, with no artifact-backed evidence of deception or exfiltration.

Install this only if you intend to use WaitSpin. Before running the earning-surface install commands, review the dry-run output because they can change editor or CLI configuration. Keep WaitSpin API keys secret, use the publisher-extension profile for installed surfaces, and treat payout or checkout flows as financial/account actions that should be user-directed.

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
83% confidence
Finding
The trigger description is extremely broad and can activate for many adjacent tasks involving onboarding, wallet status, installation, payouts, and trust/privacy reasoning. Over-broad activation increases the chance the agent invokes this skill in contexts where the user did not clearly consent to account actions, package installation, or network/API interaction, which can lead to unnecessary privileged operations or disclosure of sensitive data.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
This section contains installation and configuration-changing commands for editors and CLIs, including commands that modify status lines, hooks, plugin slots, and footer patches, but it does not require an explicit pre-execution warning or confirmation about system changes. In an agent setting, that can cause silent modification of local developer environments, potentially disrupting existing configuration or creating persistence the user did not fully understand.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal