Security audit
Optimize Prompt
Security checks across malware telemetry and agentic risk
Overview
This skill is a prompt-rewriting and audit helper with no hidden execution, persistence, credential access, or broad system authority in the reviewed artifacts.
Installers should understand that prompts may be sent to whatever model adapter they configure, so sensitive prompts should be handled according to that provider's privacy rules. The skill itself is scoped to prompt optimization and returns audit data rather than taking actions on files, accounts, or external services.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.