Security audit

China Home Appliances Sourcing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local China home-appliance sourcing reference that reads bundled data and does not show hidden access, persistence, network use, or destructive behavior.

This appears safe to install from a security perspective. Treat the bundled 2026 sourcing figures and supplier guidance as reference material, not verified live market data; independently confirm certifications, suppliers, prices, and regulations before making business decisions.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

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

Findings (4)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

Natural-Language Policy Violations

Low

Confidence: 80% confidence
Finding: The usage instructions and all example invocations are presented only in English for a skill about China sourcing, with no indication that users may interact in other languages or choose a preferred locale. This can be a natural-language policy concern when a skill implicitly constrains language without opt-in or documented justification.

Natural-Language Policy Violations

Low

Confidence: 81% confidence
Finding: This JSON file includes Chinese-language text within otherwise English content, such as the source field listing Chinese organization names. Because SQP-3 applies to all file types and flags language/locale constraints without user opt-in or justification, this is a mild policy concern where the file implicitly mixes locales without explanation.

Natural-Language Policy Violations

Low

Confidence: 78% confidence
Finding: The module docstring defines the skill exclusively as 'China home appliances' intelligence and sourcing guidance. This imposes a fixed geographic/locale scope in natural-language descriptions without any indication that users can choose another locale or that the restriction is explicitly policy-justified within the file.

Static analysis

No suspicious patterns detected.