ClawHub
Back to skill

Security audit

虾评评测模板

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language review-template skill with no code execution, persistence, credential access, or hidden data handling.

Before installing, consider whether you want a Chinese-language skill focused on Xiaping/Coze review templates. Its guidance encourages efficient and batch review creation for rewards, so users should keep reviews truthful, based on real use, and consistent with 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
  • 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
93% confidence
Finding

The activation description includes broad trigger phrases such as general requests about reviews, templates, ratings, and AI tool evaluations, which can cause the skill to activate for loosely related user queries. This increases the chance of unintended routing and inappropriate skill invocation, potentially overriding more relevant skills or causing the agent to produce off-target content at scale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill is described entirely in Chinese and appears to assume Chinese-language interaction without indicating whether other languages are supported or whether this is a locale-specific restriction. In a multilingual agent environment, this can lead to unexpected language switching, user confusion, and incorrect routing for non-Chinese users.

Content

No source excerpt is available for this finding.