ClawHub
Back to skill

Security audit

Midjourney

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Midjourney Discord guide; the main caution is that prompts and uploaded images are shared with Discord and Midjourney.

Install only if you are comfortable using Discord and Midjourney for the requested image work. Avoid uploading sensitive, private, regulated, or proprietary images or prompts unless you have confirmed the channel visibility and service terms fit your needs.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to submit prompts and upload images through Discord and Midjourney, but does not warn that this may expose sensitive content to third-party services, public or semi-public channels, retention systems, or other users depending on server/channel configuration. In a skill specifically centered on image uploads and prompt sharing, omission of privacy guidance can lead users to disclose confidential images, proprietary designs, or personal data without understanding the exposure risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.