Back to skill

Security audit

云集返利助手

Security checks for vulnerabilities and agentic risk

Overview

This is a simple markdown-only shopping rebate helper with disclosed affiliate-style recommendations and no executable code or persistence.

Before installing, be aware that this skill is intended for shopping and commission-related recommendations; users may want tighter trigger wording if they only want it invoked for explicit Yunji price, rebate, or promotion-link requests.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list is broad and generic, using short brand-related terms like '云集' and 'yunji' without clear scope restrictions. This can cause the skill to activate in loosely related conversations, increasing the chance of unintended invocation, user confusion, or inappropriate promotion behavior in contexts where the user did not explicitly request this commerce skill.

Content

No source excerpt is available for this finding.