AI Logo Generator

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:38 PM UTC
• Version:
  1.0.0

Overview

This is a disclosed logo-generation skill that uses a third-party service, cached login token, account credits, and local image downloads for its stated purpose.

Install only if you are comfortable sending logo prompts and branding details to ailogogenerator.online, storing a service token on disk, and spending 4 service credits per generated logo. Delete ~/.config/ailogogenerator.online/auth.json to log out, and ask the agent to confirm before generating multiple variants or saving files in a sensitive directory.

SkillSpector

By NVIDIA

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 (8)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The README explicitly says the skill should auto-load for broad natural-language requests like 'I need a dark techy logo,' which can cause unintended activation when a user is merely discussing branding ideas rather than consenting to invoke an external service. In this skill’s context, accidental activation is more dangerous because use may trigger browser-based authentication, spend paid credits, and send user-provided content to a third-party service.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The authentication section mentions token storage, but the skill description and installation/usage guidance do not prominently warn users up front that an authentication token will be written to disk in a persistent local file. In this context, that omission matters because users may invoke the skill conversationally without realizing it performs persistent credential storage tied to a third-party account.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The README explicitly says the skill can be auto-triggered from broad natural-language requests like 'make me a logo' or 'design an icon for my app,' even without an explicit slash command. That increases the chance of unintended invocation, which is risky here because the skill may open a browser for login, use stored credentials, make external API calls, and write files locally.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The README describes persistent token storage in ~/.config/ailogogenerator.online/auth.json, browser-based login, external API interaction, polling, image download, and local file output, but it does not prominently warn users about privacy, credential handling, or local side effects. In a skill that sends user-provided branding data to a third-party service and stores authentication material locally, the lack of explicit disclosure can lead to unintended data exposure or unsafe use on shared systems.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The skill description is broad enough to auto-trigger on general design or icon requests, which can cause the agent to invoke an external service and related side effects without sufficiently explicit user intent. In this skill, that risk is amplified because invocation can lead to reading local auth state, contacting a third-party API, consuming paid credits, and downloading files locally.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill instructs downloading the generated image into the current working directory and only announcing the saved path afterward, which creates a local file-write side effect without prior user awareness or approval. Unprompted writes can overwrite expectations about the workspace, create clutter, and in some environments may place files into sensitive or shared directories.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill reads a local authentication file and may automatically rerun a login flow, but it does not require a clear user-facing disclosure or consent before accessing local credentials. This is risky because it normalizes silent credential use and could expose account actions, spend credits, or trigger browser/login activity without the user's informed approval.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill sends user-supplied branding inputs to a third-party API without an explicit privacy disclosure, so users may unknowingly transmit business names, brand concepts, or other potentially sensitive commercial information off-platform. Because the transfer is essential to the skill's operation, the absence of disclosure and consent materially increases privacy and compliance risk.

VirusTotal

67/67 vendors flagged this skill as clean.