Back to skill

Security audit

VisHalo AI Creative Image Companion

Security checks across malware telemetry and agentic risk

Overview

This is a document-only creative prompt helper with broad activation keywords but no code, credential use, persistence, or hidden actions.

This appears safe to install as a prompt-and-briefing helper. Be aware it may trigger on generic AI image or video requests, and treat the listed VisHalo/GitHub links as external resources outside the document-only skill itself.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The manifest lists generic trigger keywords such as "ai image", "creative automation", and "ai video" without any narrowing context or exclusion conditions. These phrases overlap with common creative-workflow requests and may invoke the skill in situations unrelated to this specific VisHalo companion.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
The manifest sets the skill language to "en", which can indicate an English-only constraint, but there is no accompanying note that users may choose another language or that the restriction is required for a specific region or compliance purpose. This may violate language/locale policy expectations when no opt-in or justification is provided.

VirusTotal

2/64 vendors flagged this skill as malicious, and 62/64 flagged it as clean.

View on VirusTotal