ClawHub
Back to skill

Security audit

Alibaba Cloud AI Multimodal QVQ

Security checks across malware telemetry and agentic risk

Overview

This is a narrow Alibaba QVQ visual-reasoning helper that documents model usage and writes a local sample request file.

Safe to install for reference and sample-payload generation. Before running the helper, check the output path because it can overwrite the specified local file; if future versions add direct Alibaba Cloud API calls, review any added API key handling, image upload behavior, and network requests.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.