ClawHub
Back to skill

Security audit

直播返利助手

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed live-shopping rebate helper with no bundled code, persistence, or hidden execution behavior.

Before installing, understand that the skill is meant to help compare live-shopping prices and rebates and may guide users toward rebate links; verify prices and affiliate terms independently before buying.

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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes broad phrases such as shopping- and rebate-related terms that can match many ordinary e-commerce requests outside a tightly scoped live-streaming rebate workflow. This can cause the skill to activate unexpectedly, intercept unrelated user queries, and route users into a commerce-oriented flow they did not intend, increasing the risk of inappropriate handling of shopping decisions or links.

Content

No source excerpt is available for this finding.