Executive Summary
An incident feed lists 11 flaws across agent frameworks (LangChain, LangGraph, CrewAI, AutoGen, Microsoft Agent Framework, Google ADK), Varonis's CoSnitch one-click exfiltration in Copilot Personal, and Obsidian Security's LiteLLM gateway privilege escalation and RCE.
What Happened
This incident feed aggregates recent AI agent and LLM infrastructure vulnerabilities, including 11 flaws across major agent frameworks such as LangChain, LangGraph, CrewAI, AutoGen, Microsoft Agent Framework, and Google ADK, covering issues like insecure deserialization, SSRF, path traversal, SQL injection, and use‑after‑free.[7] It describes severe remote code execution chains, including a Microsoft Agent Framework deserialization flaw triggerable via prompt injection, unauthenticated code execution in Google ADK, LangGraph checkpointer bugs, Varonis’s CoSnitch vulnerability in Microsoft Copilot Personal enabling one‑click data exfiltration via indirect prompt injection, and Obsidian Security’s LiteLLM gateway vulnerabilities that allow privilege escalation and server code execution.[7]
Affected Products
- LangChain
- LangGraph
- CrewAI
- AutoGen
- Microsoft Agent Framework
- Google ADK
- Microsoft Copilot Personal
- LiteLLM
Vulnerability / Attack Technique
Framework flaws (deserialization, SSRF, path traversal, SQL injection) reachable via prompt injection
Technical Mechanism
Issues include a Microsoft Agent Framework deserialization flaw triggerable by prompt injection, unauthenticated code execution in Google ADK, LangGraph checkpointer bugs, and LiteLLM gateway escalation to server code execution.
AI Security Category
LLM03:2025 Supply Chain
Part of the AI Supply Chain and AI SBOM topic.
Relevant Frameworks
RealGround Analysis
Nearly every major agent framework had a serious flaw. RealGround analysis: framework versions are a core part of the AI SBOM and need a patch process.
Recommended Controls
- Inventory agent frameworks and versions in an AI SBOM
- Patch the listed frameworks and LiteLLM
- Never deserialize untrusted agent state
Related RealGround Service
Secure AI Agent Build · or start with the free AI Agent Security Scanner.
Sources
Agentic Threat Tracker / The AI Wire: https://agentic-threat-tracker.com/
Summary and analysis written by RealGround from the source above; last updated 2026-10-18.