ClawHub
Back to skill

Security audit

返利提醒官

Security checks for vulnerabilities and agentic risk

Overview

This is a simple rebate reminder skill whose notification behavior is disclosed and aligned with its stated purpose, with privacy and opt-in details users should confirm before use.

Before installing, confirm that notifications are opt-in per channel and that you can disable them easily. Use this only with rebate or coupon accounts you are comfortable connecting, and avoid sending sensitive order details through SMS or email unless you trust the integration.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes broad, everyday phrases such as '省钱提醒' and '返利通知', plus mixed-language variants, which increases the chance of accidental or unintended activation outside a clearly scoped rebate workflow. In a skill designed for proactive notifications, over-broad activation can cause the agent to enter data-handling or messaging flows without sufficiently explicit user intent, raising privacy and consent risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill defines proactive notifications across multiple channels, including WeChat, SMS, and email, but does not state consent requirements, data usage limits, or opt-in/opt-out controls. Because these channels require handling contact details, order status, coupon state, and possibly purchase behavior, missing notice and consent mechanisms creates a real risk of unauthorized messaging, privacy leakage, and user harm.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.