ClawHub
Back to skill

Security audit

propzapi-full

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward PropzAPI integration for rendering template images and webpage screenshots, with the main caution that user-provided templates, data, and screenshot URLs are sent to PropzAPI.

Install only if you are comfortable sending template contents, render variables, created templates, and screenshot target URLs to PropzAPI. Avoid putting secrets, personal data, private dashboard URLs, or tokenized links into requests unless you have confirmed that is appropriate for your use case.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill clearly uses environment-based authentication and makes outbound network requests to a third-party API, but it does not declare corresponding permissions. This creates a transparency and governance gap: users or platforms may not realize the skill can access secrets and transmit data externally, increasing the risk of unintended data exposure or policy bypass.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill encourages sending user-provided HTML/CSS, template variables, and render inputs to an external third-party service without a clear upfront warning. That can result in users unknowingly transmitting sensitive business data, personal information, or proprietary templates to propzapi.com.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The screenshot feature can capture arbitrary third-party URLs, but the documentation does not clearly warn about privacy, authorization, or legal implications. Without that warning, the skill may be used to snapshot private, authenticated, or sensitive pages and send those targets to an external service without informed consent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.