ClawHub
Back to skill

Security audit

专家会诊团

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language review-template skill with no executable payload, persistence, credential handling, or hidden data flow.

Installers should understand that this skill is written mainly in Chinese and is intended to produce advisory perspective reviews, not verified facts or professional decisions. Review any file edits before applying them, since Write/Edit are allowed even though the skill does not require automatic mutation.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description and trigger phrases are written in Chinese, while also including an English 'Use when' section that still mixes in Chinese terms, indicating the skill is effectively scoped to Chinese-language interaction. There is no statement offering language choice or requiring user opt-in for this locale constraint, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.