Deep Research
Security checks across malware telemetry and agentic risk
Overview
This is a text-only research workflow that teaches source evaluation and report structure without asking for credentials, code execution, persistence, or hidden access.
Install this if you want a structured workflow for deeper research. For high-stakes medical, legal, financial, or business decisions, set clear depth and source requirements and verify conclusions independently, because the skill may gather and summarize broad public information of varying credibility.
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.