research-harness
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only research workflow skill that gives agents guardrails for reproducible experiments and does not include executable code or hidden data access.
Install if you want a structured research-governance workflow for agents. Expect it to influence the agent to create research repo structure, manifests, validators, checkpoints, proposals, and experiment records when relevant; review those changes as you would any agent-written research infrastructure, especially before running costly model experiments or applying it to sensitive unpublished work.
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.