ClawHub
Back to skill

Security audit

Milk Tea Order Consultant

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language milk-tea recommendation prompt with no executable code, external access, or persistence.

Before installing, expect this skill to guide milk-tea choices in Chinese and to ask preference questions before recommending drinks. It does not appear to access files, accounts, credentials, networks, or persistent settings.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Confidence
93% confidence
Finding
The description and all operational instructions are written as Chinese-only behavior, with no indication that the assistant should match the user's preferred language. This can violate language/locale policy expectations when users interact in another language and are not given an opt-in choice.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation description says the workflow applies when the user says "推荐奶茶" or similar requests, but it does not define what counts as a similar request. This makes the trigger scope ambiguous and could cause unintended invocation for loosely related beverage or recommendation queries.

Static analysis

No suspicious patterns detected.