Back to skill

Security audit

ShopBack返利助手

Security checks for vulnerabilities and agentic risk

Overview

This is a small ShopBack cashback helper skill with no executable code, persistence, credential use, or privileged actions.

Before installing, be aware that the skill may steer broad cashback-related questions toward ShopBack-style results and links. There is no evidence of code execution or credential access in the inspected package.

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
  • 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
Findings (2)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The trigger phrases are broad enough to match general shopping, cashback, or regional refund-related conversations, which can cause unintended invocation of the skill outside the user's intent. This increases the risk of context hijacking, irrelevant tool activation, or accidental steering of users toward affiliate/referral flows when they were asking a general question.

Content

No source excerpt is available for this finding.