ClawHub

Blog Image Claw Skill

Security checks across malware telemetry and agentic risk

Overview

This skill coherently generates blog images through an external image API, with visible but manageable privacy and token-handling caveats.

Install only if you trust the publisher and are comfortable sending prompts and a Neta/TalesofAI token to api.talesofai.com. Use a dedicated or limited token if available, avoid sensitive draft content or secrets in prompts, and be aware that the current CLI token flag can expose the token in process listings or logs on shared systems.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)

Description-Behavior Mismatch

Medium
Confidence
98% confidence
Finding
The skill metadata claims it uses the Neta AI API, but the code actually sends prompts and credentials to talesofai.com. This is dangerous because users may provide sensitive prompts and API tokens under false assumptions about the recipient, creating a trust-boundary violation and possible credential or data exfiltration to an undisclosed third party.

Description-Behavior Mismatch

Medium
Confidence
97% confidence
Finding
The skill metadata and description claim it uses the Neta AI image generation API, but the implementation actually sends prompts and the provided token to api.talesofai.com. This is dangerous because users and calling agents may disclose sensitive content or credentials under false assumptions about the recipient service, creating a trust-boundary violation and potential credential exfiltration to an undisclosed third party.

Intent-Code Divergence

Low
Confidence
89% confidence
Finding
The file header describes a generic blog image helper, but the code is tightly coupled to a specific third-party service through hardcoded base URL and platform headers. This mismatch obscures the real external dependency and can mislead reviewers or users about where prompts and credentials are sent, reducing informed consent and making supply-chain review harder.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README explicitly instructs users to supply an API token via a command-line flag, which can expose the secret through shell history, process listings, logs, CI output, and telemetry. Because this is user-facing documentation, it normalizes an unsafe secret-handling practice and increases the chance that real credentials will be leaked during normal use.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
Accepting the API token via a command-line argument exposes it to shell history, process listings, audit logs, and agent telemetry on many systems. The risk is amplified here because the token is then immediately transmitted to a remote service, so compromise of local observability or logs can lead to account abuse.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The script transmits the full user prompt and authentication token to an external API, while only emitting generic progress logs such as 'Generating image' and 'Still rendering.' In an agent context, prompts may contain unpublished blog content, internal notes, or sensitive user data, so sending them to a third party without explicit disclosure or consent creates a meaningful privacy and data-governance risk.

External Transmission

Medium
Category
Data Exfiltration
Content
// --- Submit image generation job ---
async function makeImage() {
  const res = await fetch("https://api.talesofai.com/v3/make_image", {
    method: "POST",
    headers: HEADERS,
    body: JSON.stringify(body),
Confidence
92% confidence
Finding
fetch("https://api.talesofai.com/v3/make_image", { method: "POST"

External Transmission

Medium
Category
Data Exfiltration
Content
// --- Submit image generation job ---
async function makeImage() {
  const res = await fetch("https://api.talesofai.com/v3/make_image", {
    method: "POST",
    headers: HEADERS,
    body: JSON.stringify(body),
Confidence
92% confidence
Finding
https://api.talesofai.com/

External Transmission

Medium
Category
Data Exfiltration
Content
// --- Poll for result ---
async function pollTask(taskUuid) {
  const url = `https://api.talesofai.com/v1/artifact/task/${taskUuid}`;
  const MAX_ATTEMPTS = 90;
  const INTERVAL_MS = 2000;
Confidence
87% confidence
Finding
https://api.talesofai.com/

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal