ClawHub
Back to skill

Security audit

cross-border-patent-risk-screen

Security checks across malware telemetry and agentic risk

Overview

The skill is purpose-aligned for patent risk screening, but it can automatically upload local product images to a public URL without a clear consent or privacy checkpoint.

Install only if users are comfortable sending product images, product links, descriptions, and patent-search queries to PatSnap-related MCP services. Do not use confidential, unreleased, personal, or metadata-sensitive images unless the operator has confirmed consent and understands that the upload step may make the image publicly accessible.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly instructs uploading a user's local image via `mcp_patsnap-patent-search__upload_patent_image` to obtain a public URL, but it does not present a clear privacy warning, consent step, or data-handling limitation near that behavior. Product images can contain sensitive information such as unpublished designs, EXIF metadata, supplier identifiers, or other confidential business information, so making them publicly accessible creates a real confidentiality and data exposure risk.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.