Miniature World Generator

• Outcome: Pass
• Latest audit: May 28, 2026 at 6:01 AM UTC
• Version:
  1.0.0

Overview

This is a small image-generation skill that sends prompts and a user-provided Neta token to the expected Neta/TalesOfAI API, with no hidden persistence or unrelated local access found.

Install only if you trust the Neta/TalesOfAI service with your prompts and API token. Avoid confidential, regulated, or secret content in prompts, and prefer passing the token from an environment variable to reduce command-history and process-list exposure.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill explicitly instructs users to pass an external Neta API token and invokes a Node script that performs network-backed image generation, yet the skill metadata declares only `tools: Bash` and no explicit network permission. This mismatch is a real security issue because it hides outbound network capability from reviewers and users, increasing the chance that secrets are provided to a skill without transparent permission disclosure.

Description-Behavior Mismatch

Medium

• Confidence: 97% confidence
• Finding: The skill metadata claims it uses the Neta AI API, but the code actually sends requests to api.talesofai.com. This mismatch undermines informed consent and trust boundaries because users may provide prompts, tokens, and reference IDs believing they are interacting with one provider while their data is sent to another service.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The README instructs users to send arbitrary prompts and a bearer API token to a third-party image-generation service, but it does not clearly warn that user content and credentials are transmitted off-platform. This creates a real privacy and security transparency issue because users may unknowingly submit sensitive prompts or mishandle tokens in CLI usage, especially when examples encourage direct command-line token passing.

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: The request body includes the user prompt and may include a reference UUID, and the headers include a user-supplied token, all of which are transmitted to an external service without meaningful disclosure in the tool behavior. In a skill context, hidden third-party transmission of user content and identifiers is dangerous because users may unknowingly expose sensitive prompts, account-linked identifiers, or access credentials.

External Transmission

Medium

• Category: Data Exfiltration

Content

};
  }

  const res = await fetch('https://api.talesofai.com/v3/make_image', {
    method: 'POST',
    headers: HEADERS,
    body: JSON.stringify(body),

• Confidence: 76% confidence
• Finding: fetch('https://api.talesofai.com/v3/make_image', { method: 'POST'

External Transmission

Medium

• Category: Data Exfiltration

Content

};
  }

  const res = await fetch('https://api.talesofai.com/v3/make_image', {
    method: 'POST',
    headers: HEADERS,
    body: JSON.stringify(body),

• Confidence: 76% confidence
• Finding: https://api.talesofai.com/

VirusTotal

VirusTotal findings are pending for this skill version.