Security audit

SHEIN 电商图片生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI Hive image-generation helper for SHEIN-style fashion product imagery, with expected API-key setup, reference-image upload, task polling, and result download behavior.

Install only if you are comfortable giving this skill an AI Hive API key and uploading the specific product/reference images you choose to AI Hive. Treat ~/.ai-hive/config.json as a credential file, and use only intended image files with the upload or generate commands.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 87% confidence
Finding: The skill advertises no declared permissions, yet the documented commands and underlying tooling imply shell execution, filesystem access, environment access, and network use. This creates a transparency and consent problem: users and orchestration systems cannot accurately assess what the skill can do, increasing the chance of unintended credential exposure, local file access, or outbound network actions.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: The skill is presented as a narrow SHEIN image-generation/editing helper, but the underlying behavior reportedly includes browser-based API key setup, local credential storage, account/model querying, chat capabilities, video generation, and generic media/task management. That mismatch undermines user trust and least-privilege expectations, and could lead operators to authorize a narrowly scoped skill that actually performs broader account, data-handling, and networked actions.

Description-Behavior Mismatch

Medium

Confidence: 96% confidence
Finding: The file is presented as a SHEIN-focused image generation/editing skill, but it embeds a broad-purpose AI client supporting text chat, video generation, model enumeration, user-info access, and generic media upload. This creates a capability/scope mismatch that can expose unnecessary functions to downstream agents or users, increasing the chance of misuse, unintended data access, and policy bypass through a seemingly narrow skill wrapper.

Context-Inappropriate Capability

Medium

Confidence: 95% confidence
Finding: The skill includes a user-info endpoint that retrieves account and wallet/balance information, which is unrelated to the stated purpose of SHEIN image generation. Exposing account metadata in a narrowly scoped media skill violates least privilege and can leak sensitive operational or financial information if an agent or caller invokes it unexpectedly.

Context-Inappropriate Capability

Medium

Confidence: 94% confidence
Finding: The code contains full video-generation support despite the skill being marketed for image generation/editing. This broadens the skill’s effective authority and can be abused to access more expensive, less reviewed, or policy-distinct generation paths under the cover of an image tool.

Static analysis

No suspicious patterns detected.