test

Security checks across malware telemetry and agentic risk

Overview

The available evidence shows only a broad activation wording concern, not hidden access, data theft, destructive behavior, or other high-impact authority.

This appears safe to install based on the available signals, but users should know it may activate on broad references to its name or specialty. Review the skill’s trigger wording if accidental invocation would be disruptive in your workflow.

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: 93% confidence
Finding: The activation text is broad enough that ordinary mentions of the skill’s name or general specialty could cause the agent to invoke this skill unexpectedly. Overly permissive triggering increases the chance of unintended capability use, context confusion, or prompt-surface expansion, especially in multi-agent systems where routing decisions may be heuristic.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal