ClawHub
Back to skill

Security audit

直播带货

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple livestream-commerce planning guide with no executable behavior or hidden access requests.

Installers should understand this is a Chinese-language livestream-commerce SOP aid. Review any generated plans before applying them to business data or platform operations, especially where local compliance, personal information, or platform rules are involved.

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

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The description says to invoke the skill 'when carrying out livestream-commerce related work,' which is a broad condition without explicit trigger phrases, scope limits, or exclusion examples. This could overlap with many general business, marketing, or operations tasks and may cause unintended invocation.

Content

No source excerpt is available for this finding.