Security audit

非毒·分析魄

Security checks across malware telemetry and agentic risk

Overview

This is a simple instruction-only data analysis skill with no executable code, installs, credentials, persistence, or hidden data movement.

This skill appears safe to install as an analysis prompt/template. Review any separately installed dependent skills it mentions, and avoid giving sensitive spreadsheets or private business data to any agent workflow unless you trust the execution environment.

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: 89% confidence
Finding: The trigger guidance is broad enough to activate on generic requests like analyzing an Excel file or predicting trends, which can cause the skill to intercept ordinary user intents without clear scoping or consent. In an agent system, overbroad routing can lead to inappropriate tool/skill invocation, unnecessary data exposure to the skill pipeline, and reduced predictability of behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal