ClawHub

Materials Cli

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate schema-to-image CLI, but it should be reviewed because its AI generation path depends on missing local code and has some under-scoped credential and Windows shell handling.

Install only if you trust the publisher and can verify the missing materials-agents dependency. Prefer OPENAI_API_KEY over --api-key, avoid sensitive prompt content or untrusted custom base URLs, and be cautious running untrusted prompt or file path strings on Windows.

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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The `generate` command sends user prompts to OpenAI or a configured API endpoint, but the skill does not clearly warn users that their prompt content may leave the local environment and be processed by a third party. This creates a real privacy and data-handling risk if users include sensitive schemas, proprietary design details, or confidential text in prompts.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The CLI accepts an OpenAI API key directly via the `--api-key` command-line argument, which exposes the secret to shell history, process listings, terminal logging, and CI job output. In a developer tool that may be run locally or in shared environments, this creates a realistic risk of credential leakage even if the feature was added for convenience.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal