ClawHub
Back to skill

Security audit

Kawaii Art Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims, but users should treat prompts and the Neta API token as shared with the external image service and avoid exposing the token in shell history.

Install only from a source you trust, prefer a pinned or verified installer when available, and run the script with a token that has limited scope or quota. Do not put private personal data, secrets, or confidential material in prompts or reference identifiers, because they are sent to the external image-generation provider. Be aware that the documented --token flag can leave the token visible in shell history, process listings, or logs.

A.I.G

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)

T09 · Insecure Skill Coding Practices

Warning
Location
kawaiiartgenerator.js:8
Finding

API Token Exposed Through Command-Line Arguments

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
SKILL.md:31
Finding

Unpinned Package Execution Through npx Installation Instructions

Content
View full analysis
Remediation
View remediation

SkillSpector

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The README instructs users to run npx skills add blammectrappora/kawaii-art-generator without pinning a specific version or immutable source. This allows a future compromised or maliciously updated package or installer path to be fetched and executed on a user's machine, turning installation into a supply-chain execution risk.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The install instruction uses npx skills add blammectrappora/kawaii-art-generator without pinning a specific package/version, so users may execute whatever package version is current at install time. This creates a supply-chain risk: if the referenced package, dependency chain, or publisher account is compromised, arbitrary code could run on the user's machine during installation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This code sends user-supplied prompts and an authentication token to a third-party external API endpoint. External transmission is expected for an image-generation skill, but it still creates a real data exposure risk because any prompt content, reference UUIDs, and bearer-style token are disclosed to an outside service with no minimization, validation, or disclosure controls.

Content

Scanner excerpt · kawaiiartgenerator.js (reported line 103)May include surrounding context.

js
}

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

  let taskUuid;
  if (typeof makeRes === 'string') {

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The polling request repeatedly transmits the task UUID to the same third-party service, confirming ongoing dependence on an external system and extending metadata exposure. While less sensitive than the initial prompt submission, it still leaks workflow identifiers and creates a privacy and service-trust risk if the remote provider is compromised or logs requests aggressively.

Content

Scanner excerpt · kawaiiartgenerator.js (reported line 120)May include surrounding context.

js
const maxAttempts = 90;
  for (let i = 0; i < maxAttempts; i++) {
    await sleep(2000);
    const pollRes = await request('GET', `https://api.talesofai.com/v1/artifact/task/${taskUuid}`, null);

    const status = pollRes && pollRes.task_status;
    if (status === 'PENDING' || status === 'MODERATION') {

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The "When to use" section says to use the skill when someone asks to "generate or create kawaii art generator images," but it does not define specific trigger phrases, constraints, or negative examples. This could lead to over-invocation for loosely related requests about cute art or image creation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.