Security audit
GPT Image 2 Prompt Architect
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent text-focused prompt assistant with an optional disclosed read-only MCP integration and no evidence of hidden or unsafe behavior.
Before installing the optional MCP, users should be comfortable running an npx GitHub package and should keep it limited to the listed read-only prompt-research tools. The core skill itself is suitable as a text prompt-building workflow.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.