Security audit

China Consumer Electronics Factory

Security checks for vulnerabilities and agentic risk

Overview

This is a local consumer-electronics sourcing guide with no malicious code behavior found, but its dataset contains factory contact entries that are not accurately disclosed in the skill description.

Install only if you want a China-focused consumer-electronics sourcing reference. Be aware that the bundled dataset includes corporate factory contacts and some adjacent categories such as drones and security cameras despite the skill text describing the data as cluster-level only; verify supplier details and compliance requirements independently before using them for outreach or procurement.

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

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

Description-Behavior Mismatch

Medium

Confidence: 95% confidence
Finding: The file’s declared purpose is a buyer guide for consumer-electronics manufacturing clusters, but it also exposes a curated list of direct corporate contact emails and includes sectors that extend beyond the stated scope. This creates unnecessary data exposure and broadens the operational utility of the dataset for unsolicited outreach, targeting, or misuse beyond the skill’s advertised function.

Context-Inappropriate Capability

Medium

Confidence: 93% confidence
Finding: Including surveillance and security-camera vendors in a general consumer-electronics sourcing guide introduces a sensitive category that is materially different from the stated smartphone, wearable, audio, smart-home, and AR/VR focus. Such entries can facilitate procurement or discovery of surveillance suppliers and raise regulatory, reputational, and misuse concerns disproportionate to the skill’s declared scope.

Context-Inappropriate Capability

Low

Confidence: 90% confidence
Finding: The manifest does not mention drones or imaging systems among the covered categories. Listing DJI as a factory entry introduces an adjacent but distinct manufacturing domain that is not clearly justified by the skill's stated purpose.

Natural-Language Policy Violations

Low

Confidence: 78% confidence
Finding: The module docstring frames the skill exclusively around "China consumer electronics" intelligence and sourcing guidance. This hard-coded locale/country scope may be a policy concern if organizational guidance requires user choice or explicit justification for region-specific behavior, and no opt-in or justification appears in the file.

Static analysis

No suspicious patterns detected.