Decision Framework

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a decision-support helper with an over-broad trigger note, but no evidence of hidden access, persistence, destructive behavior, or data exfiltration.

Installers should be aware that this skill may activate for broad analysis or selection requests. If that is annoying or confusing, narrow its trigger wording or ask the agent to confirm before using it; no evidence here indicates malicious behavior.

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 trigger description is broad enough to match many ordinary requests such as '帮我分析' or '怎么选', which can cause the skill to activate in contexts beyond structured decision support. Over-broad routing increases the chance of inappropriate invocation, user confusion, and unintended capture of conversations where a more specific or safer skill should respond.

VirusTotal

41/41 vendors flagged this skill as clean.

View on VirusTotal