PowerShell Safe Chain

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only PowerShell scripting guide with no executable code, persistence, credential use, or hidden behavior.

Safe to install as a PowerShell scripting aid. Still review generated PowerShell before running it, especially commands that delete files, stop processes, or modify system state.

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
88% confidence
Finding
The self-use trigger is broad enough to activate this skill for routine PowerShell tasks, including common file operations, which can cause the agent to over-apply guidance involving execution flow, file manipulation, or command sequencing. In an automated system, overly broad invocation criteria increase the chance of unnecessary or context-inappropriate use, amplifying the risk of unintended actions even though the skill itself is not overtly malicious.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal