ClawHub
Back to skill

Security audit

Wechat Live Review

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only WeChat video-channel live commerce review guide with no code execution, persistence, or hidden system access.

Install only if you want a Chinese-language framework for WeChat Video Account live-commerce review. Use aggregated, authorized business metrics and avoid pasting personal contact lists, individual chat records, raw customer identifiers, or other personally identifiable data.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes generic phrases like '直播复盘' and '数据分析' that are broad enough to match many unrelated user requests, causing the skill to activate outside its intended scope. Over-broad invocation can expose users to irrelevant guidance, accidental processing of unrelated business data, and misrouting of requests to a skill that expects specialized platform context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs analysis of user demographics, purchase behavior, private-domain traffic, group/friend referrals, and enterprise WeChat follow-up data, but provides no privacy notice, consent boundary, minimization guidance, or handling restrictions. This creates a risk that operators will input personally sensitive or account-linked data into the skill without proper authorization or safeguards, leading to privacy violations or inappropriate downstream use.

Content

No source excerpt is available for this finding.