ClawHub

Quotation Generator

Security checks across malware telemetry and agentic risk

Overview

This skill has a legitimate quote-generation purpose, but it should be reviewed because it can send customer-facing quotes, update CRM records, and run follow-ups with limited scoping.

Install only if you are comfortable giving the agent tightly scoped access to customer, pricing, messaging, and CRM systems. Require explicit owner approval before every customer send, verify recipients and pricing, limit what is shared over WhatsApp, and make scheduled follow-ups visible and easy to cancel.

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 to activate during ordinary sales interactions, including generic customer quote requests and pipeline stage changes. In a skill that can draft and send commercial documents and update CRM records, ambiguous invocation increases the risk of unintended quote generation, premature outreach, or incorrect state changes based on incomplete context.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The workflow explicitly sends draft and final quotes through WhatsApp and to customers without any controls for sensitive business or customer data handling. Because quotes include customer identity, pricing, terms, and potentially proprietary product details, transmitting them through external channels without consent, classification, or verification can cause data leakage, misdelivery, regulatory exposure, and commercial harm.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal