GPT Image 2 Prompt Architect
Security checks across malware telemetry and agentic risk
Overview
This is a text-only prompt-writing skill for AI image prompts, with no executable code or autonomous access, though its marketplace tags include unrelated purchase and crypto labels.
Reasonable to install for prompt-writing assistance. Treat it as a third-party GPTImg2.art prompt workflow reference, not an official OpenAI tool, and do not rely on it for payments, purchases, crypto activity, account support, or API integration.
Publisher note
Text-only prompt design skill for GPT Image 2 workflows. It has no scripts, no binaries, no API keys, no environment variables, and no autonomous network access. Public references point to GPTImg2.art docs, generator, prompt gallery, and raw SKILL.md.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- 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
VirusTotal
VirusTotal findings are pending for this skill version.