Back to skill

Security audit

Ziztu Faceless YouTube

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: the completed AIG scan found no issues, while Skillspector flagged a privacy concern about sending user content to Ziztu.

The verdict is benign, but consider whether you are comfortable sharing video ideas, titles, promises, or reference URLs with Ziztu. Skillspector's scan was partial: it noted a missing reference and did not analyze binary content, so the evidence is incomplete.

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 workflow submits user content to Ziztu without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

This step instructs the agent to give the user's video idea, title and promise, or reference URL to an external service. Although Ziztu is clearly named, the skill does not warn that this shares potentially unpublished or confidential user content with a third party.

Content

No source excerpt is available for this finding.