ClawHub
Back to skill

Security audit

Image Studio — AI Image Prompt System

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static prompt-writing guide for AI images and does not request sensitive access or run code.

Before installing, understand that this skill may be invoked for a wide range of image, branding, and social-media prompt requests. It appears low-risk because it is only a Markdown guide, but users who prefer tighter activation should narrow its description to specific marketing image prompt use cases.

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
For a markdown file, broad activation or applicability language can function like an ambiguous trigger. Saying the skill is for "any platform and niche" provides almost no boundary on scope and could overlap with many general content-creation requests.

Vague Triggers

Medium
Confidence
90% confidence
Finding
This wording does not define meaningful boundaries for activation and may cause unintended invocation for generic image or branding requests. The file does not provide negative examples or explicit constraints that would limit use to a narrower context.

Static analysis

No suspicious patterns detected.