Back to skill

Security audit

Ziztu Cinematic Depth

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign because the scans reported no clear security threat; confidence is medium because Skillspector coverage was partial.

The verdict is benign, but not risk-free. Consider whether the English-only template suits your needs. Skillspector marked its analysis partial: a local reference was missing, and binary content was outside its analysis scope, 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 paste-ready dialogue template hard-codes English without offering a language choice.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The dialogue template specifies [English] as a fixed language tag rather than a user-selected placeholder. Because these templates are presented as paste-ready, this defaults generated speech to English without user opt-in or a documented model requirement.

Content

No source excerpt is available for this finding.