ClawHub
Back to skill

Security audit

Stained Glass Art Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed third-party image generator that sends prompts to Neta/TalesOfAI, with no evidence of hidden or unrelated behavior.

Install only if you trust Neta/TalesOfAI with your image prompts, optional reference image UUIDs, and API token. Avoid sensitive or regulated content in prompts, and prefer a limited or revocable token.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill declares only `tools: Bash` but its documented usage explicitly requires a Neta API token and invokes a remote image generation service, which implies network access. Undeclared network capability is a real security concern because it can mislead reviewers and users about what data may leave the environment, especially when prompts or tokens may be transmitted to a third party.

External Transmission

Medium
Category
Data Exfiltration
Content
console.error("");

async function createTask() {
  const res = await fetch("https://api.talesofai.com/v3/make_image", {
    method: "POST",
    headers,
    body: JSON.stringify(body),
Confidence
92% confidence
Finding
The hardcoded remote domain indicates this skill is designed to exfiltrate generated content inputs to an external service. In context this is likely intentional functionality rather than malware, but it still creates a trust boundary issue: users may assume a local art tool while their prompt, token, and optional reference identifiers are transmitted to a remote API controlled by another party.

External Transmission

Medium
Category
Data Exfiltration
Content
console.error("");

async function createTask() {
  const res = await fetch("https://api.talesofai.com/v3/make_image", {
    method: "POST",
    headers,
    body: JSON.stringify(body),
Confidence
92% confidence
Finding
The hardcoded remote domain indicates this skill is designed to exfiltrate generated content inputs to an external service. In context this is likely intentional functionality rather than malware, but it still creates a trust boundary issue: users may assume a local art tool while their prompt, token, and optional reference identifiers are transmitted to a remote API controlled by another party.

Static analysis

No suspicious patterns detected.