ClawHub

Quotation Generator

Security checks across malware telemetry and agentic risk

Overview

This sales automation skill appears purpose-aligned, but it may contact customers through WhatsApp and update CRM records without clearly bounded confirmation steps.

Install only if you are comfortable giving the agent access to customer, pricing, WhatsApp, and CRM workflows. Require a human approval step before any message is sent or any CRM record is updated, and confirm the intended customer, quote contents, recipient, and CRM status each time.

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
89% confidence
Finding
The trigger conditions are broad enough that the skill could activate on loosely matched sales conversations or generic owner instructions, causing quote generation or customer-facing actions without clear, deliberate invocation. In this context, unintended activation is more dangerous because the workflow includes sending drafts over WhatsApp and updating CRM state, which can expose customer data, send inaccurate quotations, or create incorrect business records.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill describes transmitting quote drafts and customer information via WhatsApp and writing sales status into a CRM without an explicit warning, consent boundary, or data-handling notice. That omission increases the risk that users will unknowingly expose sensitive business or personal data through third-party channels and persist inaccurate or unauthorized records in internal systems.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal