Security audit
model-aware-prompt-optimizer
Security checks across malware telemetry and agentic risk
Overview
This skill is a prompt-rewriting helper with clear scope and no executable or persistent behavior.
This skill is appropriate if you want help rewriting prompts for different AI models. Before installing, note that it can rely on provider reference guidance and may suggest checking official docs for newly released models, but the artifacts do not request access to credentials, files beyond its own references, or system-changing actions.
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.