Back to skill

Security audit

Gothic Portrait Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent image generator, but it uses an API token and broad shell execution with under-scoped install and credential-handling instructions that users should review before installing.

Install only if you are comfortable sending prompts, reference image IDs, and a Neta token to the external image service. Prefer a pinned or ClawHub-managed install path, avoid putting real tokens in shell history or logs, and rotate any token already used in command-line examples.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Findings (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:32
Finding

Unpinned Remote Package Execution in Installation Instructions

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
gothicportraitgenerator.js:3
Finding

API Token Exposed Through Command-Line Arguments

Content
View full analysis
"your prompt" --token YOUR_TOKEN ``` The same credential-handling pattern is documented in `README.md:22-26`: ```bash node
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README clearly instructs users to send prompts and optional reference-image identifiers to a third-party image-generation API, but it does not warn that user content will leave the local environment or discuss privacy, retention, or handling by the external service. This can lead users to unknowingly transmit sensitive personal, proprietary, or biometric-related content to an external provider. The skill context increases the concern because portrait generation and reference-image use can involve identifiable people and stylistic source material.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
84% confidence
Finding

The README instructs users to install or invoke the skill via npx skills without pinning a specific package version. That exposes users to supply-chain risk because a newly published or compromised package version could be fetched and executed at install time. In the context of an agent skill, this is more dangerous because users are likely to copy-paste the command directly and execute remote code immediately.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill declares tools: Bash and documents use of an external API token plus a Node-based invocation, but it does not define any permissions or allowed-tools scope despite requiring network access. This can cause the agent runtime to grant broader-than-necessary capabilities or leave network use insufficiently constrained, increasing the risk of unintended external requests and token exposure.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L20 says to use the skill when someone asks to "generate or create gothic portrait generator images," which is awkward and underspecified as an activation condition. It does not clearly bound the trigger phrases or provide exclusion examples, increasing the chance of unintended invocation from broadly similar image-generation requests.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
81% confidence
Finding

The install instruction uses npx skills add omactiengartelle/gothic-portrait-generator without pinning a specific version. This makes installs non-reproducible and exposes users to supply-chain risk if the package or dependency resolution changes, is hijacked, or a malicious update is published later.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The code hardcodes an outbound HTTPS destination to api.talesofai.com while the skill metadata and token acquisition instructions reference neta.art, creating a vendor-mismatch red flag. That mismatch makes the external transmission more dangerous because users may believe they are authorizing one service while their prompt data and token are actually sent to another.

Content

Scanner excerpt · gothicportraitgenerator.js (reported line 73)May include surrounding context.

js
async function main() {
  // Submit the image generation task
  const createRes = await fetch("https://api.talesofai.com/v3/make_image", {
    method: "POST",
    headers,
    body: JSON.stringify(body),

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The code hardcodes an outbound HTTPS destination to api.talesofai.com while the skill metadata and token acquisition instructions reference neta.art, creating a vendor-mismatch red flag. That mismatch makes the external transmission more dangerous because users may believe they are authorizing one service while their prompt data and token are actually sent to another.

Content

Scanner excerpt · gothicportraitgenerator.js (reported line 73)May include surrounding context.

js
async function main() {
  // Submit the image generation task
  const createRes = await fetch("https://api.talesofai.com/v3/make_image", {
    method: "POST",
    headers,
    body: JSON.stringify(body),

External Transmission

Medium
Category
Data Exfiltration
Confidence
86% confidence
Finding

The polling request repeatedly contacts the same third-party service and sends the authentication header on each attempt. While this is functionally part of asynchronous job handling, it expands credential exposure and network dependency, and in combination with the provider/domain mismatch it increases the blast radius if the remote service is untrusted or compromised.

Content

Scanner excerpt · gothicportraitgenerator.js (reported line 106)May include surrounding context.

js
for (let attempt = 0; attempt < 90; attempt++) {
    await new Promise(resolve => setTimeout(resolve, 2000));

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