ClawHub
Back to skill

Security audit

article-image

Security checks for vulnerabilities and agentic risk

Overview

This is a simple article-image recommendation skill that does not request execution, credentials, persistence, or file/network access.

Safe to install if you want Chinese-language help drafting article image search ideas. Still verify image licenses yourself before use, especially for commercial publishing or paid/portfolio image sources.

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
Confidence
88% confidence
Finding
The listed invocation phrases such as "帮我找几张配图", "推荐一个封面图", and especially the template "找一张 xxx 相关的图片" are common conversational requests and do not define clear scope or exclusion conditions. Because the skill description provides no negative examples or contextual constraints, these triggers could overlap with ordinary chat and cause unintended activation.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The section title explicitly states "按主题（英文关键词）" and all recommended search terms are provided only in English, which imposes a specific language choice in the skill's prescribed output behavior. There is no opt-in, alternative locale handling, or explanation that the image sources require English queries.

Static analysis

No suspicious patterns detected.