Back to skill

Security audit

Ecommerce After Sales Reply

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Chinese ecommerce after-sales reply template with no code, persistence, or hidden data access.

Install this if you need standardized Simplified Chinese after-sales replies. Provide accurate platform rules, order facts, shop policies, and limits, because the skill is a drafting template and should not be used to promise refunds, returns, or exceptions beyond the applicable rules.

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
  • 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
  • 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
97% confidence
Finding

The markdown explicitly requires output in Simplified Chinese only, which is a language/locale constraint. Under the policy, forcing a specific language without user choice or documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This instruction hard-codes Chinese output in the core prompt template and does not provide any language selection mechanism. That creates the same locale-policy issue within the reusable invocation template itself.

Content

No source excerpt is available for this finding.