Back to skill

Security audit

Share to GetNote

Security checks across malware telemetry and agentic risk

Overview

The skill appears to do what it claims: import a user-provided ChatGPT or Gemini share link into GetNote, with disclosed browser tooling setup and user confirmation before saving.

Install this only if you are comfortable with uv/Playwright installing browser automation dependencies locally and with copied share-link content being saved into your GetNote account. Review the extracted note titles and contents before confirming the save step, especially for private conversations.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill instructs the agent to execute shell commands (`uv run ...`) and install dependencies/browser components, but it declares no permissions. This creates an undeclared execution surface that can fetch remote content and run local tooling, increasing the risk of unexpected code execution or environment changes without explicit user/operator approval.

Context-Inappropriate Capability

Medium
Confidence
77% confidence
Finding
The script automatically downloads and installs Chromium when a cache path is missing, which exceeds the narrowly expected behavior of parsing a shared link. In an agent/skill context, silent host modification and network retrieval of large executables increase attack surface, violate least privilege, and may be unexpected in restricted environments.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.