Building Rag Applications With Langchain
Security checks across malware telemetry and agentic risk
Overview
This is a simple instructional LangChain RAG skill with no executable install hooks, persistence, credential handling, or hidden behavior in the packaged artifacts.
This appears safe to install as a learning/reference skill. Treat the sample code as incomplete tutorial material: review and choose any LangChain, FAISS, or model-provider packages yourself before installing or running code in a real project.
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.