ClawHub
Back to skill

Security audit

dmxapi-image-generation

Security checks for vulnerabilities and agentic risk

Overview

This is a small image-generation skill that calls a MiniMax API with a user-provided key, with no hidden execution, persistence, or local data access found.

Before installing, treat any prompt or image sent through this skill as data shared with MiniMax, and avoid using sensitive, regulated, or confidential material unless that is intended. Configure only a MiniMax API key you are comfortable using for image generation.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The manifest description says the skill should be used when the user needs to generate images or do AI drawing, which is a wide natural-language trigger without clear boundaries or exclusion conditions. This can overlap with many ordinary creative requests and does not specify when this skill should or should not activate.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly instructs use of an external image-generation API and requires an API key, but it does not clearly warn that user prompts and possibly attached image-editing inputs will be transmitted to a third-party service. This creates a real privacy and compliance risk because users may provide sensitive text or images without informed consent, and the broad image-generation context increases the chance of sharing personal or confidential content externally.

Static analysis

No suspicious patterns detected.