Xiaolongxia Assistant

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:17 PM UTC
• Version:
  1.0.1

Overview

This appears to be a development-helper skill with command examples, not a hidden or self-executing payload.

Install only if you want an agent to help with plugin development workflows. Before running any generated install, publish, or rollback command, confirm the target project, registry/account, credentials, and expected side effects; prefer dry runs or backups where available.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill explicitly instructs the agent to provide directly executable install, publish, and rollback commands, but it includes no requirement to warn users about side effects, verify environment assumptions, or require confirmation before potentially changing the system. In a plugin-development context, such commands can install packages, modify local files, publish artifacts, or alter project state, increasing the risk of unsafe copy-paste execution by users.

VirusTotal

63/63 vendors flagged this skill as clean.