Adaptive Expert Interview
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed LLM-guided expert interview workflow with local state/export files and no evidence of hidden or malicious behavior.
Use this only when you intentionally want an LLM-assisted expert interview. Avoid entering confidential or regulated information unless authorized, expect answers and analysis to be saved in local state/export files, and verify the referenced Python engine and prompt files are available before relying on it.
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
63/63 vendors flagged this skill as clean.