Build

Security checks across malware telemetry and agentic risk

Overview

This is a very broad build-themed prompt skill, but it contains only a short markdown instruction file and no executable or hidden behavior.

Install only if you want a general creation/build prompt. Give it explicit boundaries for each task, especially before any infrastructure, deployment, code execution, hardware design, or organizational change.

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: 95% confidence
Finding: The skill is described as a broad, foundational engine for creating software, infrastructure, and organizational structures, but it provides no activation boundaries, approval requirements, or domain limits. In an agent setting, this kind of unconstrained scope can enable unsafe overreach, causing the agent to initiate high-impact actions or generate sensitive operational artifacts without sufficient gating.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal