Security audit

公众号爆款封面生成与编辑

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed image-generation helper that sends user-provided prompts and optional images to a fixed AI Hive API and stores its API key locally.

Install only if you are comfortable sending article prompts and any selected reference images to AI Hive. Use authorized, non-sensitive images, protect the stored API key, and review generated covers before publishing.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill exposes code execution capabilities including network, shell, file read/write, and environment access, yet declares no permissions or user-facing constraints. In this context, the skill also instructs use of external scripts and a remote API, so the missing permission declaration can hide meaningful data exfiltration and filesystem access risks from users and policy enforcement.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill explicitly states that keyed requests must be sent to a fixed third-party API, but it does not clearly warn users that prompts, reference images, and possibly sensitive local assets will leave the system. Because this skill handles uploaded or local photos such as authorized interviewee and event images, silent off-system transmission creates privacy, confidentiality, and credential-handling risk.

VirusTotal

54/54 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.