ClawHub
Back to skill

Security audit

Live Shopping

Security checks for vulnerabilities and agentic risk

Overview

This is a small markdown-only live-shopping guidance skill with no executable code, install hooks, persistence, credential handling, or hidden authority.

Before using it, treat it as shopping advice only: verify sellers and discounts yourself, do not share passwords, payment details, or verification codes, and avoid using it for automated purchases, bot-like red-envelope grabbing, or actions that may violate platform rules.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill promotes flash-sale participation and red-envelope interactions but does not warn users about privacy exposure, account misuse, impulse purchasing, or platform-rule risks tied to high-pressure live-commerce flows. In this context, the lack of warnings makes the skill more dangerous because it is centered on time-sensitive shopping behavior that often involves account credentials, payment data, and promotional engagement mechanics.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example invocations use highly generic placeholders like '具体场景任务' and '核心功能' without clearly bounding the skill’s intended use. This can cause an agent to over-trigger the skill in unrelated shopping or recommendation contexts, increasing the chance of unintended invocation and unsafe automation around purchases or account-linked actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.