ClawHub

OpenAI Image CLI

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward OpenAI image CLI skill with expected privacy, credential, local history, and npm package trust considerations.

Install only if you trust @versatly/openai-image-cli and its publisher. Prefer environment variables or secure secret storage for API keys, avoid submitting sensitive images or prompts unless approved, and clear local history after sensitive work.

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

Medium
Confidence
92% confidence
Finding
The skill encourages generating and editing images via a remote OpenAI service but does not warn users that local images, prompts, and possibly embedded metadata will be transmitted off-host. In this context, users may upload sensitive photos, documents, or proprietary visuals, so the omission can lead to accidental privacy or confidentiality exposure.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation presents storing the API key in CLI config as a normal authentication path without any warning about local plaintext storage, file permissions, shell history leakage, or multi-user system exposure. This can cause credential compromise if users paste secrets into commands or store them in insecure config files.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The skill states that history tracking is enabled by default without warning that prompts, file paths, model usage, and related metadata may be written to local storage. On shared machines or sensitive workflows, this can leak private project details or create unexpected forensic traces.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal