Infra

Security checks across malware telemetry and agentic risk

Overview

This is a broad infrastructure guidance skill with no code, hidden access, or automatic system-changing behavior.

This skill may give advice about production infrastructure and security-sensitive systems. Review and test any recommendations yourself before applying changes to live cloud accounts, networks, IAM, secrets, or incident-response workflows.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (1)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The skill description and body cover a very wide range of infrastructure topics, including incident response, architecture, cloud, security, and IaC, without clear activation boundaries. In an agent setting, this can cause over-broad invocation on routine conversations, increasing the chance the agent applies powerful infrastructure guidance in the wrong context or acts without sufficient scoping and user confirmation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal