ClawHub
Back to skill

Security audit

社媒营销图片套组｜Social Carousel Campaign

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AI image-generation helper that uploads only user-specified source images to AI Hive and saves generated outputs locally.

Install only if you are comfortable sending the source images and generated prompt content you provide to AI Hive. Use the brief command when you only want to inspect the prompt, avoid passing private images unless intended, and protect the stored API key in ~/.ai-hive/config.json.

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
88% confidence
Finding
The skill instructs users to run local Python commands that read files, write downloaded outputs, use environment variables such as SKILL_PATH, invoke shell execution, and make outbound network requests to an external API, yet the skill declares no corresponding permissions. This creates a trust and review gap: operators may execute a skill with broader capabilities than expected, and unauthorized local files or sensitive data could be exposed to the external service if the script is modified, misused, or later expanded.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.