LangChain
Named by 35 kept items in this workspace.
17 items name it under classification.technologies, 10 under affected products and 8 under tools.
The items that name it 35
Framework providing middleware example for checking prompts, tool calls, tool results, and responses
Agent development framework that has adopted MCP as a first-class integration layer.
One of eleven vulnerabilities across agent frameworks involving insecure deserialization, SSRF, path traversal, use-after-free
Modular framework for building LLM-powered agentic workflows including security automation
AI agent framework honeypotted; targeted in blind prompt injection attacks.
Referenced as a real tool used in agentic pattern labs (mentioned alongside LangGraph, CrewAI, AutoGen for multi-agent systems).
agent framework providing building blocks, often used underneath a harness
affected by LangGrinch vulnerability (CVE-2025-68664) across 847 million downloads
Unpinned specifiers like langchain>=0.1.0 produce zero default-report findings (heuristic tier only, --paranoid)
Agent orchestration framework, evaluated for inherent vulnerabilities such as session memory poisoning or recursive loop hijacking
vulnerable to code injection (CVE-2023-29374)
optional integration framework; guardrails layer can wrap LangChain chains/Runnables
agentic framework covered by inkog and piighost integrations
local file store
AI agent framework mentioned as similarly foundational to the AI agent ecosystem (subject of future research in the series)
Agent pipeline framework supported by OWASP Agent Memory Guard's detection middleware and sanitization hooks
In every workspace you can read 61
Security
AI
All technologies in this workspace.