Back to skill

Security audit

Divorce

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local divorce-organization helper, but it can store very sensitive financial details in plaintext on the user's device.

Install only if you are comfortable keeping divorce-related financial information on this device. Use device or filesystem encryption, avoid entering unnecessary account numbers or identifiers, and delete the files under the divorce memory folder when you no longer need them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill clearly instructs the agent to read and write sensitive divorce-related data under `memory/divorce/`, but it declares no permissions. That mismatch is a real security issue because the platform and users are not given accurate visibility into the skill's filesystem capabilities, especially for highly sensitive financial, custody, and legal-preparation information.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script stores highly sensitive divorce-related financial data, including asset descriptions, values, and ownership status, in a predictable plaintext file under the user's home directory without any warning, consent flow, access control, or encryption. In the divorce context, this information is especially sensitive because disclosure could expose a user's financial position, joint assets, and legal strategy to local attackers, other users on the same system, backups, or malware.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.