Back to skill

Security audit

Refund Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent refund/return helper with no artifact evidence of hidden execution, credential access, network use, or destructive behavior.

Install this if you want Chinese-language guidance for Taobao, Tmall, JD, or Pinduoduo-style refund workflows. Treat generated return reasons and compensation requests as drafting help only, and make sure any claims and evidence are truthful and platform-appropriate.

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
93% confidence
Finding

The skill description is broad enough to trigger on ordinary user conversations about refunds, returns, or exchanges, which can cause unintended invocation. Over-broad routing increases the chance that the skill handles requests outside its intended scope, potentially leading to poor decisions, irrelevant advice, or interference with other safer or more appropriate skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill content strongly biases usage toward Chinese-language interactions and examples without stating whether this is a required locale limitation or giving users a choice. This can cause misrouting, exclusion of non-Chinese-speaking users, or unexpected behavior when the system selects the skill despite the user's language preferences.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file presents the skill as a bilingual title but all user-facing guidance, step descriptions, error messages, and generated application templates are fixed in Chinese. This can violate language/locale policy because the skill does not offer user opt-in or selection for the output language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.