ClawHub
Back to skill

Security audit

Vpick Ai Image Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a clearly disclosed image-generation connector that sends prompts and reference images to VPick and model providers, with some ordinary privacy and billing considerations.

Install this only if you are comfortable using VPick as the image-generation backend. Treat the MCP URL as a password, avoid sending sensitive prompts or private reference images unless intended, and watch VPick credit usage because generations can spend account balance.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises very broad activation phrases like 'generate image', 'create an image', and 'create illustration', which are common user intents and can cause the skill to be invoked in situations where the user did not specifically intend to use this third-party service. Because the skill routes prompts and uploaded images through VPick and external model providers and uses an embedded MCP credential, over-broad activation increases the risk of unintended data disclosure, unexpected billing, and accidental use of a credentialed external connector.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.