ClawHub
Back to skill

Security audit

Live Review Six Steps

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Douyin live-stream review checklist with no code execution, persistence, credential access, or hidden actions.

Installers should treat this as operational guidance, not verified platform policy; the broad '数据分析' trigger may make it appear for unrelated analysis requests, and the claimed 2026 Douyin rules should be independently checked before business decisions.

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 (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list includes broad, common terms such as '数据分析' that can match many unrelated user requests, increasing the chance this skill is invoked outside its intended Douyin live-review context. Unintended invocation can cause irrelevant guidance, user confusion, and accidental exposure of platform-specific operational advice in contexts where it does not apply.

Static analysis

No suspicious patterns detected.