ClawHub
Back to skill

Security audit

Ecommerce Video Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed e-commerce video generation helper, but submit mode can send product scripts and images to an external AIGC service.

Install only if you are comfortable with storyboard text, product image data, and related payload metadata being saved locally and, when --submit is used, sent to the configured AIGC service. Use preview mode first and avoid submitting unreleased or confidential product material unless that external service is approved for it.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The documentation describes submitting video-generation requests to an external API and constructing payloads that include compressed script text and product reference images, but it does not clearly warn users that this local content will be transmitted off-system. Because the skill is part of an e-commerce content pipeline, these assets may contain proprietary marketing copy, unreleased product imagery, or other sensitive commercial material.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly states that, in chat environments, results will also be output to the chat window, but it does not warn that generated payloads or compressed script content may contain sensitive business data and product details. In an agent setting, echoing such content into chat increases the risk of unintended disclosure to logs, operators, or other integrations even if no direct code exploit is involved.

Content

No source excerpt is available for this finding.