Back to skill

Security audit

芬香返利助手

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language JD/Fenxiang rebate assistant skill with no executable code, install hooks, persistence, or hidden system behavior.

Before installing, understand that this skill is aimed at Chinese JD/Fenxiang rebate and social promotion workflows. Use any generated referral or promotion links transparently, avoid unsolicited mass sharing, and disclose affiliate or promotional relationships where platform rules or law require it.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

All visible natural-language content, including the name, description, triggers, and output format, is presented only in Chinese, with no indication that users may choose another language. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale limitation is explicitly justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill explicitly plans to generate promotion copy and links for sharing in social groups, but it provides no warning about referral tracking, disclosure obligations, or privacy risks when distributing affiliate links. In this context, the omission can mislead users into sharing promotional material without understanding that links may contain identifiers or that recipients may be exposed to unsolicited marketing.

Content

No source excerpt is available for this finding.