ClawHub
Back to skill

Security audit

电商售后客服应答

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow Chinese customer-service reply template with no code execution, data access, persistence, or hidden behavior.

This is appropriate to install if you want reusable simplified-Chinese aftersales reply drafting. Users should still review generated replies for case-specific policy accuracy, refund or compensation authority, and any required platform wording before sending.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
If information is incomplete, do not invent operational facts. Draft a safe response that explains the current known position and asks for only the minimum missing information needed to proceed.

## Output Rules

Always output in simplified Chinese unless the caller explicitly asks otherwise.
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The instruction says to always output in simplified Chinese unless the caller explicitly asks otherwise. This imposes a language preference by default rather than offering the user or operator a language choice up front, which matches the locale/language policy violation criteria.

Static analysis

No suspicious patterns detected.