Security audit

Amazon 亚马逊电商图片生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its image-generation purpose, but it stores an API key locally and can send that key to any configured API endpoint.

Review this skill before installing. Only use the default AI Hive endpoint unless you fully trust a custom endpoint, because the API key is sent with requests. Expect reference images and generated outputs to pass through AI Hive, and remove or rotate the key in ~/.ai-hive/config.json if you no longer want it stored locally.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/imagegen.py:95
Finding: API Credential Disclosure Through an Unrestricted Custom Base URL
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Note

Location: SKILL.md:66
Finding: Unpinned Runtime Dependency Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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

Findings (8)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 94% confidence
Finding: The skill invokes a Python script, installs a package, and supports task execution, which implies shell, network, file, and environment access, yet it declares no explicit tool restrictions. This creates an overprivileged execution surface: an agent may grant broader capabilities than necessary, making misuse or prompt-injection-driven abuse more likely if the script or surrounding runtime is compromised.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The description includes Chinese text alongside English, but the file does not state that the skill is intended specifically for Chinese-speaking users or offer language/locale selection. This can create an implicit language policy issue because the skill surface is not consistently localized or opt-in by user preference.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The module docstring describes this file as a general-purpose AI Hive tool supporting text chat, image generation, video generation, model querying, media upload, and task polling, and the code implements those generic capabilities via chat/video/model/user-info commands. That is broader than the skill manifest, which claims an Amazon catalog image generation/editing skill focused on creating and editing e-commerce imagery.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The init flow persists the API key to ~/.ai-hive/config.json without an explicit warning that a long-lived credential will be stored on disk. Although the code sets file permissions to 0600, users may still unknowingly leave sensitive credentials resident on shared, backed-up, or synchronized systems, increasing the chance of credential exposure and unauthorized API use.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This markdown file contains substantive natural-language content exclusively in Chinese, but does not state that the skill is Chinese-only, region-specific, or user-selectable by locale. Under the policy rule for language/locale, forcing a specific language without opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The example API key placeholder uses Chinese text ('请替换为你的APIKey'), which imposes a specific language in user-facing configuration content. There is no accompanying opt-in, alternative language, or justification for a locale-specific constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The module docstring and user-facing CLI strings are written in Chinese, and the skill does not offer users a language/locale option. This can violate language/locale policy when a skill implicitly forces one language without opt-in or justification.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The init flow launches the user's browser to an external chat/login page using webbrowser.open, which is not an obvious requirement of an Amazon image-generation/editing skill itself. While useful for setup, it is an additional local-system capability outside the core stated purpose of creating and editing catalog images.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.