LangGraph Tutor
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only LangGraph tutoring skill whose tool, memory, and multi-agent guidance is disclosed and aligned with its stated purpose.
Safe to install as a LangGraph instructional skill. When applying its patterns, be careful with any tools or database-backed checkpoints you add: require approval before sensitive actions, isolate memory by user or task, and avoid storing secrets in graph state.
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.