Security audit
GPT Image 2 Prompts
Security checks across malware telemetry and agentic risk
Overview
This is a Markdown-only helper for writing GPT Image 2 prompts, with no evidence of hidden commands, data access, or persistence.
Reasonable to install for image-prompt writing. Treat any uploaded reference images or personal visual details as normal chat data, and only share private photos or brand assets if you are comfortable using them in the session.
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
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.