Security audit
LLM as Judge
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only skill for getting a second AI model to review complex work, with no executable code or hidden local access.
Safe to install as a review workflow. Before using it on confidential code, security designs, trading systems, or internal planning documents, make sure you are comfortable sharing that context with another model provider and avoid including secrets unless necessary.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.