Back to skill

Security audit

Ziztu Viral Reels

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign verdict with medium confidence: no malicious behavior was reported, though one finding flags that user content may be sent to Ziztu without a privacy warning.

Before installing, consider whether you are comfortable with user-provided topics being sent to Ziztu, and avoid submitting personal or confidential information. Evidence is incomplete: Skillspector marked its analysis partial because a local reference was missing and binary image content was outside its analysis; the separate AIG scan completed with no findings.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The generation workflow submits user content to Ziztu without a privacy warning.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The workflow instructs the agent to enter the user's topic into Ziztu and preview a generated script, rather than merely listing the service. Although Ziztu is named, the skill does not warn that this sends user-provided content to a third-party service or advise against submitting confidential or personal information.

Content

No source excerpt is available for this finding.