Skip to content
Threat Feed
Subscribe

Vendor

LangChain

3 briefs RSS
medium advisory

Detection of Local LLM Model File Creation on Endpoints

This brief describes how the creation of Large Language Model (LLM) files, including formats like .gguf, .safetensors, .ggml, and Modelfiles, by local AI inference frameworks such as Ollama, llama.cpp, GPT4All, and LM Studio can be detected on Windows endpoints, indicating potential shadow AI deployments, unauthorized model downloads, or rogue LLM infrastructure which poses data exfiltration risks and policy violations.

Ollama +9 shadow-it llm data-exfiltration policy-violation endpoint shadow-ai local-llm intellectual-property-theft +2
2r 5t
high advisory

LangSmith SDK Untrusted Manifest Deserialization Vulnerability

The LangSmith SDK is vulnerable to untrusted manifest deserialization when pulling public prompts via `pull_prompt`, potentially leading to SSRF, prompt injection, or sensitive data exposure; CVE-2026-45134.

langsmith +2 deserialization ssrf prompt-injection
2r 3t
high advisory

LangChain Unsafe Deserialization Vulnerability

LangChain is vulnerable to unsafe deserialization of attacker-controlled objects through overly broad `load()` allowlists, potentially leading to persistent chat-history poisoning, prompt injection, credential disclosure, or server-side requests.

langchain-core langchain deserialization vulnerability
2r 1t