ClawHub
Back to skill

Security audit

E-Commerce Return & Refund Prompt

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed customer-service prompt template for return and refund replies, with no bundled code or persistence, though implementers should harden how buyer text is inserted into prompts.

Before installing, confirm this fits a Chinese-language support workflow or set the language explicitly. If you automate it, treat buyer-provided text as untrusted data, validate fields like issue_type and days_since_delivery, isolate free-text reasons from instructions, and keep human approval for refunds, compensation, legal, safety, or high-value disputes.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:64
Finding

Untrusted Buyer Data Is Directly Interpolated into an Instruction-Bearing LLM Prompt

Content
View full analysis
Remediation
View remediation

SkillSpector

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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The inputs section states that the language field defaults to zh-CN, which means the skill will use a specific locale even when the user has not chosen one. The policy requires offering language choice or clear justification for locale constraints; neither is provided here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.