ClawHub
Back to skill

Security audit

handraw-style

Security checks for vulnerabilities and agentic risk

Overview

This skill is a non-executable prompt reference for hand-drawn image styles and does not request sensitive access or run code.

Installers should expect this to help phrase image-generation prompts using numbered style references. Review the upstream catalog if you need exact meanings for each number, and be aware the skill may activate on general requests about hand-drawn visual style consistency.

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)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The 'Trigger Conditions' section lists general situations like needing help with art styles or wanting visual consistency, but it does not define specific activation phrases, boundaries, or exclusion conditions. In a skill-routing context, these broad descriptions could overlap with many ordinary image-generation requests and cause unintended invocation.

Static analysis

No suspicious patterns detected.