Security audit

AliExpress 速卖通电商图片生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

This skill is an AI Hive image-generation helper for AliExpress listing graphics, with expected API-key, upload, and download behavior, though users should avoid relying on unused generic client code bundled in the script.

Install only if you are comfortable sending selected product/reference images to AI Hive and storing an AI Hive API key locally. Use the documented generate, task, upload, and init commands, and avoid adapting the unused generic client functions unless you intentionally want broader AI Hive account or media capabilities.

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 (6)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill invokes shell commands, reads and writes local files, accesses environment variables, and performs network operations, yet declares no permissions or capability boundaries. This creates a transparency and consent failure: an agent or user may invoke the skill expecting only image generation, while it can also touch local state and external services without explicit declaration.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: The documented purpose is narrowly scoped to AliExpress image generation/editing, but the underlying behavior reportedly includes generic chat, video generation, account and wallet retrieval, model enumeration, arbitrary media upload, browser launching, and credential/config writes. This scope mismatch is dangerous because it can mislead users and orchestrators about what the skill may do, enabling unexpected data exfiltration, credential handling, or broader API actions than intended.

Description-Behavior Mismatch

Medium

Confidence: 95% confidence
Finding: The file is a generic AI Hive client that exposes chat, model listing, user-info, upload, and video-generation capabilities far beyond the declared AliExpress image-generation/editing purpose. This scope expansion increases attack surface and may let downstream agents invoke unintended networked features, including account and media operations, under the guise of a narrowly scoped skill.

Context-Inappropriate Capability

Low

Confidence: 88% confidence
Finding: The skill includes a user-info endpoint that retrieves account details and wallet balance, which are unrelated to ecommerce image editing. Even if authenticated access is required, exposing this through the skill unnecessarily broadens access to sensitive account metadata and can leak billing information to callers or logs.

Context-Inappropriate Capability

Medium

Confidence: 93% confidence
Finding: Video-generation support is inconsistent with the skill's stated image-generation/editing role and introduces additional upload, tasking, and download paths. That enlarged capability surface can be abused to process unintended content types, increase data exfiltration opportunities, or trigger higher-cost actions outside the expected user consent boundary.

Intent-Code Divergence

Medium

Confidence: 90% confidence
Finding: The module advertises itself as a generic AI capability tool rather than a narrowly tailored AliExpress image skill, signaling intentional overbreadth. In agent environments, such mismatch is dangerous because orchestration logic and users may trust the manifest scope while the code quietly enables broader authenticated actions.

Static analysis

No suspicious patterns detected.