Create a Self-Selling Website

• Outcome: Review
• Latest audit: Sep 10, 2026 · 4:57 PM UTC
• Version: 1.0.1

Overview

The skill appears to be a legitimate EvoWeb website-generation integration, but it may send business details to an external service, consume credits, and create hosted websites without requiring clear user confirmation first.

Install only if you intend to use EvoWeb as a third-party hosted website generator. Before invoking it, confirm that the prompt can be sent to EvoWeb, that using account credits is acceptable, and that the generated site may become hosted on EvoWeb infrastructure. Avoid including secrets, private customer data, regulated information, or confidential business plans unless you are authorized to share them with that service.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The skill description is broad enough that it could be invoked for many generic website-related requests without clearly signaling limits, prerequisites, or when it should not be used. Overly broad activation increases the chance the agent routes user requests into this external-service workflow unexpectedly, which can lead to unintended data sharing and unwanted credit consumption.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The workflow directs the assistant to send the user's business description to an external API but does not require a clear disclosure or consent step before transmission. Users may include confidential business plans, customer details, or regulated information, and the skill as written could exfiltrate that content to a third party without informed approval.

External Transmission

Medium

• Category: Data Exfiltration

Content

**Perfect for:** Businesses that want to be discovered by AI assistants and convert AI-driven traffic into paying clients

**API Base URL:** `https://api.evoweb.ai/openapi/api/v1`

## Authentication

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.