Brandomica Lab

Security checks across malware telemetry and agentic risk

Overview

The skill looks like a normal brand-checking helper, but its advertised service and npm install target appear closed or stale, so users should review it before installing. ([brandomica.com](https://www.brandomica.com/))

Install only if you understand this may no longer function as advertised. The skill text itself is not malicious, but the official publisher page says the service and MCP server are closed; avoid submitting confidential launch names unless you verify the current package, service ownership, and data handling first. ([brandomica.com](https://www.brandomica.com/))

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: 93% confidence
Finding: The skill encourages users to submit prospective brand names to checks spanning domains, social platforms, trademarks, app stores, Google, and SaaS channels, but it does not warn that these queries may disclose confidential or pre-launch names to external services. For stealth launches or trademark-sensitive workflows, premature disclosure can leak strategy, create monitoring signals, or weaken business confidentiality even if the tool is functioning as intended.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal