ClawHub
Back to skill

Security audit

Qlik Cloud

Security checks across malware telemetry and agentic risk

Overview

This Qlik Cloud skill is mostly purpose-aligned, but it exposes broad business-tenant access and state-changing actions without enough scoping or confirmation guidance.

Review before installing. Use a scoped, least-privilege Qlik API key, store it outside shared or committed files, and require explicit user confirmation before deleting apps, starting or canceling reloads, running automations, or triggering alerts. Verify the missing referenced scripts from a trusted source before providing credentials.

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
93% confidence
Finding
The skill description is broad enough to trigger on generic analytics, dashboard, business data, or Qlik-adjacent requests, which can cause the agent to invoke this powerful integration when the user did not clearly ask for Qlik Cloud operations. In this skill, over-triggering is more dangerous because it exposes high-privilege capabilities including tenant inspection, user/license enumeration, natural-language querying of business data, and state-changing actions.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill documents destructive and state-changing operations such as app deletion, reload triggering/cancellation, automation execution, and alert triggering without any explicit confirmation, authorization, or safety checks. In an agent setting, this increases the risk of unintended or prompt-induced actions that alter production analytics assets or workflows, potentially causing data disruption, operational impact, or loss of availability.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.