ClawHub

Nvidia Sdxl

Security checks across malware telemetry and agentic risk

Overview

This skill does generate images as advertised, but it ships with an embedded NVIDIA API credential and sends prompts to NVIDIA under that credential.

Review before installing. The image-generation behavior is coherent, but the embedded NVIDIA API key should be removed and rotated, with users supplying their own credential through a secret or environment variable. Do not include confidential, personal, or proprietary information in prompts, and expect generated files to persist locally with an absolute file path returned.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Low
Confidence
89% confidence
Finding
The skill explicitly states that generated images are saved locally and that the tool returns an absolute local file path, but it does not warn users that this may reveal internal workspace directory structure. Exposing absolute paths can leak environmental details that aid follow-on probing or prompt users to request access to sensitive local files.

Missing User Warnings

High
Confidence
99% confidence
Finding
A live API credential is hardcoded directly in the source code, which makes it easy to leak through source control, logs, packaging, or downstream redistribution of the skill. Anyone who obtains the file can use the key to make unauthorized API calls, incur costs, or impersonate the application against the NVIDIA endpoint.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill sends user-supplied prompt content and optional negative prompts to a third-party API without any user-facing notice, consent flow, or minimization. If users include sensitive or proprietary information in prompts, that data is transmitted off-host to an external service, creating privacy, compliance, and data handling risk.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal