ClawHub
Back to skill

Security audit

Controlled Generation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Runware ControlNet image-generation guide, with the main caveat that user images may be processed by an external service.

Installers should understand that this skill is guidance for using Runware image-processing APIs. Do not use confidential, regulated, private, or proprietary images unless you are comfortable sending them to that service and have reviewed its retention and access terms.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to provide a source image and send it through external preprocessing and image generation services, but it does not warn that the image data may leave the local environment and be processed by a third party. This can lead to unintended disclosure of sensitive photos, proprietary designs, floor plans, or personal images, especially because the skill explicitly encourages uploads of user-provided assets for transformation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The examples instruct users to send source images and derived guide-image URLs to a third-party image service, but they do not disclose that user-provided images may leave the local environment and be stored or processed remotely. This creates a real privacy and data-handling risk, especially when users may upload personal photos, interiors, floor plans, or other sensitive visual content under the assumption that the skill is only giving transformation guidance.

Content

No source excerpt is available for this finding.