Research
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only research planning skill that asks the agent to clarify scope, save a confirmed outline, and then proceed to report structuring.
Install this if you want the agent to slow down and create a user-approved research outline before writing reports. Expect it to ask clarifying questions, review only the materials you provide, save a Markdown outline, and then use a follow-up report-outline step.
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.