ClawHub
Back to skill

Security audit

思齐的三国演义读书笔记

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese reading-note helper for Romance of the Three Kingdoms with no code, network access, persistence, or credential handling.

Install this if you want a Chinese-language study helper for 三國演义 chapter notes. Before relying on it for schoolwork, consider tightening the activation phrase and making language expectations explicit, but there is no evidence of malicious or high-risk behavior.

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)

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The description and content are entirely in Chinese and present the skill as tailored to a specific user without indicating any language choice or opt-in. Under the policy, forcing a specific language without offering the user a choice can be a natural-language policy violation.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The activation text is very broad: '告诉我想读第几回，即可获得读书笔记' does not define clear invocation boundaries, so the skill could be triggered in loosely related reading or homework contexts without explicit user intent. This is not directly harmful code execution, but it can cause unintended activation, response hijacking, or confusion when multiple skills could match similar educational requests.

Static analysis

No suspicious patterns detected.