Back to skill

Security audit

Pdd Food Category Master

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language advisory skill for Pinduoduo food-category store operations, with no executable code or hidden persistence.

Before installing, treat this as business guidance rather than guaranteed legal, tax, food-safety, or platform-compliance advice. It is best suited for Chinese-language Pinduoduo food sellers; confirm regulated decisions with current platform rules and qualified professionals.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill metadata and content are entirely Chinese-oriented and do not provide any mechanism for honoring the user's language preference or locale, which can cause the skill to respond in an inaccessible language. This is primarily a usability and safety-of-operation issue because misunderstandings in compliance, platform policy, or food-safety guidance can lead to incorrect execution by users.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list is overly broad and includes common e-commerce phrases such as food operations, traffic drops, complaints, and category ranking, which can activate the skill in many ordinary conversations outside a narrowly intended use case. In a high-impact business-operations skill, overbroad invocation increases the chance the agent applies prescriptive guidance in the wrong context, causing unintended behavior, irrelevant advice, or user confusion.

Content

No source excerpt is available for this finding.