Test

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward helper for rendering and AI-generating JSON schemas, with expected OpenAI API use but no evidence of hidden or harmful behavior.

Before installing, verify that materials-cli is the intended trusted package and prefer a pinned version. Use a limited OpenAI API key, avoid passing secrets on the command line, and do not include confidential data in generation prompts unless that provider use is approved.

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: 95% confidence
Finding: The skill exposes a `generate` command that sends user-supplied prompts to an external AI service via OpenAI-compatible API settings, but the documentation does not clearly warn users that their prompt content leaves the local environment. This creates a real privacy and data-handling risk because users may provide sensitive text, proprietary schema descriptions, or internal context under the assumption the tool is purely local.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal