Process Interviewer
Security checks across malware telemetry and agentic risk
Overview
This skill is a discovery interview guide that stays within its stated purpose and does not include code, installs, persistence, or external actions.
This appears safe to install as an interview and planning aid. It may ask which tools, accounts, data sources, or credential types are involved in a workflow, but it does not ask the agent to collect secret values or perform actions; avoid pasting real passwords, tokens, or private credentials into the conversation.
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.