ClawHub
Back to skill

Security audit

Codex Imggen

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Codex CLI image-generation wrapper, with expected network and proxy behavior for that purpose.

Install only if you are comfortable using Codex CLI for image generation. Do not submit confidential prompts, private images, client artwork, or regulated data unless your Codex account and local proxy configuration are approved for that data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly routes image generation through Codex CLI with proxy enabled by default and supports sending prompts plus optional reference images, but it does not warn that this content may be transmitted to external services or through a local proxy. In practice, users may unknowingly send sensitive prompts, proprietary artwork, or personal images off-host, creating privacy, compliance, and data-handling risks.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The script unconditionally exports `http_proxy` and `https_proxy`, defaulting to `http://127.0.0.1:1080`, before invoking `codex exec`. This silently forces all network traffic for the child process through a proxy, which can redirect, observe, or alter requests and may cause sensitive prompts or referenced image data to transit an unintended intermediary.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script exports http_proxy/https_proxy and invokes `codex exec`, which will transmit the user-provided prompt and optional reference image over the network, but it does not explicitly warn the user that their content may leave the local machine. In this skill's context, users may supply proprietary prompts or sensitive local image files via `-i`, so silent network transmission increases the risk of unintended data disclosure.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.