Back to skill

Security audit

E-commerce After-sales Responder

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language ecommerce after-sales response template skill with no code execution, persistence, or hidden data flows.

Install only for Chinese-language ecommerce support workflows. Operators should add their own privacy rules for minimizing order identifiers and photos, using approved support channels, and avoiding storage or sharing outside the support system.

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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description and instructions are entirely framed as a Chinese customer-service response generator, including mandated phrasing conventions, but there is no statement that use of Chinese is optional or limited to a China-specific deployment. This can violate language/locale policy when a skill forces a specific language without user opt-in or explicit justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger condition is broad enough to activate on general conversations containing common after-sales or customer-service keywords, which can cause unintended routing and irrelevant instruction injection into unrelated chats. In an agentic environment, over-broad activation increases the chance of the skill influencing responses outside its intended scope, reducing reliability and potentially causing inappropriate business guidance.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The guidance explicitly instructs collection of order numbers, tracking numbers, delivery status, and damage photos, which can contain personal or sensitive customer data, but it provides no minimization, masking, retention, or secure-handling guidance. In a customer-service skill, this omission can lead agents or downstream systems to over-collect or mishandle customer data, increasing privacy and compliance risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The document presents all operational instructions and response templates only in Chinese, which can amount to forcing a specific language absent any documented user choice. The policy allows locale constraints when they are explicit and justified, but this file does not state that it is limited to Chinese-speaking users or provide an opt-in/alternative.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.