ClawHub
Back to skill

Security audit

Waifu Gen Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward remote image generator, but users should treat prompts and API tokens as data shared with the Neta service.

Before installing, be comfortable with using Neta's remote API: your prompt, optional reference UUID, and token are sent to api.talesofai.com. Prefer a pinned or ClawHub-managed install path, avoid putting real secrets in shell history, and rotate the Neta token if you have already pasted it into commands 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)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:30
Finding

Unpinned Third-Party Installer Execution

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
waifugen.js:11
Finding

API Token Exposed Through Command-Line Arguments

Content
View full analysis
). Pass it via the `--token` flag. ```bash node
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README describes sending prompts and optional reference image UUIDs to an external image-generation API but does not clearly warn users that their input data is transmitted to a third-party service. This creates a privacy and data-handling risk, especially if users include sensitive prompts or assume processing is local. Because the skill centers on remote generation, the omission is more significant: external transmission is core behavior and should be disclosed prominently.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The README instructs users to install and run the skill via npx skills without pinning a specific version. That means execution depends on whatever package version is current at install/run time, creating a supply-chain risk if the package is updated maliciously or unexpectedly changed. In this context, users are explicitly encouraged to execute the command, which makes the exposure real rather than theoretical.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill invokes a script that calls an external image-generation API and therefore has network capability, but the manifest does not declare any tool scope such as permissions or allowed-tools. That makes the skill's effective capabilities less transparent to users and reviewers, increasing the risk of unintended outbound requests or abuse if the implementation changes or is swapped.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The install instruction uses npx skills without a pinned version, which allows whatever version is current at execution time to run. This creates a supply-chain risk: a compromised or incompatible upstream package version could execute unexpected code during installation or change behavior without review.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The hardcoded external endpoint confirms that data is sent off-host to a remote API. In this skill context, that is expected for image generation, but from a security perspective it still creates data exfiltration and third-party dependency risk, especially because prompts, reference IDs, and authentication material are all tied to the outbound request.

Content

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

js
}

async function createImage() {
  const res = 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 hardcoded external endpoint confirms that data is sent off-host to a remote API. In this skill context, that is expected for image generation, but from a security perspective it still creates data exfiltration and third-party dependency risk, especially because prompts, reference IDs, and authentication material are all tied to the outbound request.

Content

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

js
}

async function createImage() {
  const res = await fetch("https://api.talesofai.com/v3/make_image", {
    method: "POST",
    headers,
    body: JSON.stringify(body),

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

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

js
}

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

  for (let i = 0; i < maxAttempts; i++) {

Static analysis

No suspicious patterns detected.