Back to skill

Security audit

Pinup Art Generator

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward image-generation skill that uses a third-party API, but users should handle prompts and API tokens carefully.

Install only if you are comfortable sending your image prompt, optional reference UUID, task metadata, and Neta/TalesOfAI API token to the documented remote image service. Prefer a limited-purpose token and avoid placing real secrets in shared shell history, logs, or CI output.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (9)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill declares only the Bash tool, but its documented usage clearly invokes a Node script that calls the external Neta API using a user-supplied token, which implies network access. Undeclared network capability is risky because users and enforcement systems may not realize the skill can transmit prompts and credentials to a third-party service, reducing transparency and weakening permission controls.

Description-Behavior Mismatch

Medium
Confidence
98% confidence
Finding
The skill metadata claims it uses the Neta AI API, but the code actually sends prompts, reference IDs, and credentials to talesofai.com. This mismatch is dangerous because users may consent to one vendor while their data is transmitted to another, creating a supply-chain and trust-boundary violation that can expose sensitive prompts or tokens to an unexpected third party.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The README instructs users to supply an API token and send text prompts and optional reference-image identifiers to a third-party image-generation service, but it provides no privacy, retention, or data-sharing warning. This can cause users to unknowingly transmit sensitive prompts, creative assets, or account-linked data to an external provider, increasing the risk of data exposure or unexpected secondary use.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger guidance, 'Use when someone asks to generate or create pin up art generator images,' is broad and imprecise, which can cause the skill to activate in loosely related contexts. Overbroad invocation increases the chance of unintended use, potentially sending user prompts or tokens to an external image service when the user did not clearly intend to invoke this specific third-party skill.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The CLI sends the user's prompt and optional reference identifier to a remote image-generation service without a clear, explicit warning or consent step. In this skill context, prompts and refs may contain personal, proprietary, or sensitive creative material, so silent transmission increases privacy and data-handling risk.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
Accepting the API token via a command-line flag exposes it to shell history, process listings, audit logs, and CI job output. That can lead to credential disclosure and unauthorized use of the account or API quota if other local users or monitoring systems can read command arguments.

External Transmission

Medium
Category
Data Exfiltration
Content
console.error(`→ Submitting job (${dims.width}×${dims.height})...`);

  const submitRes = await fetch('https://api.talesofai.com/v3/make_image', {
    method: 'POST',
    headers,
    body: JSON.stringify(body),
Confidence
90% confidence
Finding
fetch('https://api.talesofai.com/v3/make_image', { method: 'POST'

External Transmission

Medium
Category
Data Exfiltration
Content
console.error(`→ Submitting job (${dims.width}×${dims.height})...`);

  const submitRes = await fetch('https://api.talesofai.com/v3/make_image', {
    method: 'POST',
    headers,
    body: JSON.stringify(body),
Confidence
90% confidence
Finding
https://api.talesofai.com/

External Transmission

Medium
Category
Data Exfiltration
Content
for (let attempt = 0; attempt < 90; attempt++) {
    await new Promise((r) => setTimeout(r, 2000));

    const pollRes = await fetch(`https://api.talesofai.com/v1/artifact/task/${taskUuid}`, {
      headers,
    });
Confidence
87% confidence
Finding
https://api.talesofai.com/

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.