ClawHub
Back to skill

Security audit

Multi Shot Video

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent guide for making multi-shot videos with Runware models, with only normal external-provider privacy considerations.

Before installing, understand that video prompts and any anchor images you provide may be processed by external video providers through Runware. Avoid confidential, personal, copyrighted, or otherwise sensitive assets unless you are authorized to send them to that service.

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
  • 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

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The PixVerse example instructs use of external image URLs as anchor frames and enables audio generation without warning that referenced images and prompt content will be transmitted to a third-party video service. This creates a real privacy and data-handling risk if users supply sensitive images, copyrighted material, or unintentionally include personal data, even though the example is instructional rather than overtly malicious.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.