ClawHub
Back to skill

Security audit

E-Commerce After-Sales CS

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only Chinese e-commerce after-sales customer service skill with no code execution, persistence, or hidden data access.

Install only if you want Chinese-language after-sales reply drafting. Review and adjust the example language to avoid accidental guarantees or commitments outside your store policy.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
93% confidence
Finding

The skill metadata and all instructional content are written as a Chinese-only customer service response skill, describing standardized reply generation in Chinese without any opt-in or alternative language handling. This creates a natural-language locale policy concern because the skill appears to require a specific language by default rather than offering language choice or documenting why the locale restriction is necessary.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill’s own policy forbids absolute-guarantee language, yet the compensation example says '我们一定尽力让您满意'. In a prompt-only customer service skill, inconsistent examples are likely to be copied verbatim by an agent or model, undermining compliance guidance and potentially creating unauthorized service commitments or customer dispute risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.