Xhs Md2img

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Markdown-to-XHS image rendering skill with disclosed external AI/image-service use and no evidence of hidden persistence, exfiltration, or destructive behavior.

Install this only if you are comfortable with Markdown content or derived prompts being processed by configured AI/image providers. Disable AI backgrounds or cloud upload for private material, use scoped API keys, and pin dependency versions for reproducible deployments.

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
82% confidence
Finding
The manifest description advertises broad Markdown-to-image conversion capabilities but does not constrain when the skill should be invoked or what classes of content are appropriate. In an agent setting, this can cause over-selection of the skill for unrelated user inputs, leading to unnecessary network/file access and unintended exfiltration of user content to external services mentioned in the skill.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal