ClawHub
Back to skill

Security audit

AI Writing Agent

Security checks for vulnerabilities and agentic risk

Overview

This is a simple writing assistant skill with no code execution or data access; the only notable caveat is broad routing and Chinese-language examples.

Install this if you want a basic structured writing helper. Be aware it may prefer the title/SEO/body/summary/CTA format and may produce Chinese output unless the user or host agent asks for another language.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
96% confidence
Finding
The skill content describes and exemplifies Chinese-language output behavior without any user opt-in, which can override user expectations and create undesired instruction precedence during invocation. While not directly enabling code execution or data theft, it can degrade integrity of responses by forcing a language the user did not request.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The invocation examples are extremely generic writing requests that overlap with ordinary user prompts, which increases the chance the platform routes unrelated requests into this skill unexpectedly. That can cause prompt squatting or misrouting, where this skill intercepts broad writing tasks without clear user intent to invoke it.

Static analysis

No suspicious patterns detected.