Cheese Brain

Security checks across malware telemetry and agentic risk

Overview

This is a coherent local knowledge-base skill, but it needs Review because it normalizes persistent searchable storage of sensitive contacts, config, tokens, and credentials without clear control boundaries.

Install only if you are comfortable with a local persistent memory database. Do not store raw passwords, API keys, OAuth tokens, recovery codes, or regulated personal data in it; store references to a password manager instead. Review the external GitHub repository before installing, protect the ~/.cheese-brain directory and backups, and require confirmation before the agent adds or updates persistent entries.

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: 84% confidence
Finding: The skill explicitly encourages storing and retrieving highly sensitive operational data such as contact details, URLs, schedules, integration identifiers, and even mentions credentials in the freeform JSON field. Although later text advises against storing secrets in plain text, the earlier examples normalize putting sensitive information into a persistent knowledge base without a strong privacy warning, retention guidance, or access-control discussion.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal