ClawHub
Back to skill

Security audit

Hot Topics

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple guide for fetching Chinese social-media trend lists from a disclosed third-party API, with no bundled executable code or persistence.

Install this if you want an agent to fetch Chinese platform trend lists from 60s.viki.moe. Be aware that using it makes third-party network requests, and prefer invoking it only for Weibo, Zhihu, Baidu, Douyin, Toutiao, or Bilibili trend requests.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill's activation guidance is broad enough to match many generic requests about trends or popular discussions, which can cause an agent to invoke this skill more often than users would reasonably expect. That increases the chance of unnecessary third-party API calls and disclosure of user queries or context to an external service, even when a general answer would suffice.

Missing User Warnings

Low
Confidence
92% confidence
Finding
The examples instruct direct requests to a third-party API without an explicit warning that using the skill sends data and metadata off-platform. In an agent setting, this can create unnoticed external data flows and reduce informed consent, especially if future implementations interpolate user-provided terms into requests or send requests automatically.

Static analysis

No suspicious patterns detected.