Back to skill

Security audit

Zencreator Video.Skill

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward guide for using an external NSFW video generator, but it asks the agent to control a logged-in browser and upload local files without clear consent or privacy safeguards.

Review this before installing if you are not comfortable letting an agent operate a logged-in ZenCreator.pro session. Only use it with files you intentionally select for upload, confirm before spending credits, and do not rely on the artifact's privacy claim without checking ZenCreator.pro's current terms and privacy practices yourself.

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
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
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to upload a local image file from the user's machine to an external third-party service, but it does not provide any user-facing warning, consent step, or guidance about the privacy and data-transfer implications. This is especially risky because the service is a remote NSFW content platform and the uploaded files may be sensitive, personal, or regulated content.

Static analysis

No suspicious patterns detected.