Back to skill

Security audit

Ecommerce Returns Reply

Security checks for vulnerabilities and agentic risk

Overview

This is a simple customer-service reply template for ecommerce returns, with no code execution, data access, persistence, or hidden behavior.

Install this only for Chinese-language ecommerce customer-service workflows. Review the return-policy reference for your platform before relying on the suggested timeframes or fee rules, and consider narrowing activation phrases if you use many customer-service skills together.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file is entirely framed as a Chinese customer-service reply template and instructs the agent to respond in that mode, but it does not state that the user must opt into Chinese or that the skill is limited to a Chinese-language environment. This can violate language/locale policy when applied to users who did not request Chinese output.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes very common customer-service terms such as '退款', '运费', and '售后', which can cause the skill to activate in broad or unintended contexts. This can route unrelated conversations into a rigid returns-policy flow, producing incorrect guidance or overriding a more appropriate skill, especially in multi-skill environments.

Content

No source excerpt is available for this finding.