ClawHub
Back to skill

Security audit

Vpick Ai Video Creator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly disclosed VPick cloud video-generation connector, with expected paid generation and media-sharing risks but no artifact-backed malicious behavior.

Install this only if you intend to use VPick for cloud-based, credit-consuming AI video/audio/image generation. Treat the MCP URL like a password, avoid sending sensitive or private media unless you are comfortable with VPick and its model providers processing it, and check credits before large generations.

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
96% confidence
Finding

The skill advertises very broad trigger phrases such as 'create a video', 'generate video', and 'add voiceover', which overlap with common user intents and can cause the agent to invoke this external cloud-connected skill too eagerly. Because the skill uses an embedded MCP credential and can trigger billable generations, over-broad routing increases the chance of unintended third-party data sharing, unwanted actions, and unexpected charges.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.