ClawHub
Back to skill

Security audit

Quack Sdk

Security checks across malware telemetry and agentic risk

Overview

The skill appears purpose-aligned for Quack SDK setup, but its quickstart handles live credentials and external actions with insufficient user control and warning.

Review the quickstart before running it. Treat it as a live setup command: it may register an agent, send a real message, and persist credentials locally. Install only if you trust the Quack service and publisher, then restrict permissions on ~/.openclaw/credentials/quack.json and rotate credentials if that file may have been exposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrases are broad enough to activate this skill in loosely related contexts, which can cause unintended use of network-registration or messaging guidance. In a skill that facilitates external API access and agent registration, overbroad invocation increases the chance of accidental outbound actions or disclosure of credentials/workflow details.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The quickstart command performs state-changing network actions—agent registration and sending a test message—without a prominent warning or confirmation step. Users may run it expecting a harmless setup example, which can create external accounts, transmit data, and consume credentials or network resources unintentionally.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.