Back to skill

Security audit

1688 Distribution User Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language 1688 distribution guide skill that provides advice and links, with no code execution or hidden persistence.

Before installing, understand that this skill is mainly useful for Chinese-language 1688 distribution workflows and may steer users toward store authorization, listing automation, and purchasing settings. Review any 1688 or downstream-platform permissions yourself before authorizing a store or enabling automatic ordering/refunds.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description contains broad trigger phrases and catch-all examples around common e-commerce questions, which can cause the skill to activate for ordinary marketplace conversations beyond its intended scope. Over-broad invocation increases the chance that specialized instructions override the base assistant in irrelevant contexts, causing misrouting, reduced answer quality, or unintended disclosure of linked internal guidance/resources.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instructions are written as if the assistant should always answer in Chinese, without preserving user language preference or stating a justified constraint. This can create unsafe or inaccessible behavior in multilingual settings by preventing accurate communication, consent, or comprehension when the user asks in another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The entire skill reference is written exclusively in Chinese and gives no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.