AI Sec Watch: A Security Intelligence Platform for AI Systems

Luu, T.J.

v0.14.5

infonewsLLM-Specific

industry

Source: LlamaIndex Security ReleasesOctober 15, 2025

Summary

LlamaIndex v0.14.5 is a release that fixes multiple bugs and adds new features across its ecosystem of AI/LLM tools. Changes include fixing duplicate node positions in documents, improving streaming functionality with AI providers like Anthropic and OpenAI, adding support for new AI models, and enhancing vector storage (database systems that store AI embeddings, which are numerical representations of text meaning) capabilities. The release also introduces new integrations, such as Sglang LLM support and SignNow MCP (model context protocol, a standard for connecting AI tools) tools.

Classification

Attack SophisticationTrivial

AI Component TargetedFramework

Affected Vendors

LlamaIndexAnthropicOpenAIxAI

Related Issues

high

Anthropic accuses Chinese AI labs of mining Claude as US debates AI chip exports

Same vendorTechCrunch

info

Anthropic doesn’t trust the Pentagon, and neither should you

Same vendorThe Verge (AI)

Original source: https://github.com/run-llama/llama_index/releases/tag/v0.14.5

First tracked: February 14, 2026 at 03:00 PM

Classified by LLM (prompt v3) · confidence: 85%