ClawHub
Back to skill

Security audit

Image 2 商品精修

Security checks across malware telemetry and agentic risk

Overview

This is a coherent AI product-photo retouching skill, but users should protect their AI Hive API key and remember that selected images are uploaded to AI Hive.

Install only if you are comfortable uploading the chosen product and QC images to AI Hive. Prefer AI_HIVE_API_KEY or a protected config file over pasting the API key into command history, use --preview before paid uploads, and verify generated results against the original and QC sources before publishing.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill instructs users to run a local Python script with filesystem, shell, environment, and network access, but it does not declare those capabilities or permissions up front. This is dangerous because users and policy systems cannot accurately assess the trust boundary before execution, increasing the chance of unintended local file access, credential use, or outbound network activity.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The description contains a very broad set of trigger keywords spanning many tools, platforms, and generic image-editing scenarios, which can cause the skill to be invoked in contexts the user did not intend. While not code execution by itself, overbroad routing increases the risk of accidental activation and unnecessary exposure of local files or API-backed operations.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill tells users to pass an API key directly on the command line or store it in local config, but it does not warn that command-line secrets may be captured in shell history, process listings, logs, or insecure local files. In a skill that performs networked API operations, this raises the likelihood of credential exposure and downstream account misuse.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.