ClawHub
Back to skill

Security audit

Replace In Video

Security checks for vulnerabilities and agentic risk

Overview

This skill gives clear instructions for a targeted video replacement workflow and discloses the main likeness and rights concerns without installing code or adding persistence.

Install only if you are comfortable sending the source video and reference images to the video inference provider used by your Runware tools. Do not use confidential, regulated, or identifiable-person media unless you have the rights, consent, and a clear understanding of the provider's handling and retention terms.

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

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The examples instruct users to send source videos and reference images to third-party video inference services and emphasize operational details like async polling, but they do not prominently warn that these assets may contain sensitive biometric, personal, or confidential information. In this skill's context, the omission is more concerning because the examples explicitly involve recasting real people and uploading identifiable face imagery, which increases privacy, consent, and data-handling risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.