ClawHub
Back to skill

Security audit

Watercolor Art Generator

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward watercolor image generator that uses a disclosed external API, with the main caution being prompt and token exposure to that service.

Install only if you are comfortable sending image prompts, optional reference IDs, and a Neta API token to api.talesofai.com. Prefer a revocable token, avoid sensitive prompt content, and be aware that passing tokens on the command line can expose them through shell history or local process listings.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README instructs users to send free-form prompts and an API token to a third-party image generation service, but it does not disclose privacy, retention, or data-sharing implications. This can mislead users into submitting sensitive text or credentials without understanding that their data is leaving the local environment and may be stored, processed, or used by an external provider.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger guidance, 'Use when someone asks to generate or create watercolor art generator images,' is overly broad and weakly scoped. Broad invocation criteria can cause the skill to activate in loosely related contexts, increasing the chance of unnecessary tool execution or unintended routing to a Bash-capable skill that requires a user-supplied token.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill sends the user-provided prompt and authentication token to a third-party API, but the code does not present any explicit user-facing disclosure at the point of transmission. In an agent skill context, this is a real privacy and credential-handling concern because users may not realize their inputs and secrets are being sent off-platform to an external service.

External Transmission

Medium
Category
Data Exfiltration
Content
};
  }

  const makeRes = await request('POST', 'https://api.talesofai.com/v3/make_image', makeBody);

  const taskUuid = typeof makeRes === 'string' ? makeRes : makeRes.task_uuid;
  if (!taskUuid) {
Confidence
84% confidence
Finding
https://api.talesofai.com/

External Transmission

Medium
Category
Data Exfiltration
Content
process.exit(1);
  }

  const pollUrl = `https://api.talesofai.com/v1/artifact/task/${taskUuid}`;
  const maxAttempts = 90;

  for (let i = 0; i < maxAttempts; i++) {
Confidence
76% confidence
Finding
https://api.talesofai.com/

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.