Skip to content
OpenAdvisories
High · 7.5 CVE-2024-12704 EUVD-2025-7006GHSA-j3wr-m6xh-64hgPYSEC-2025-244PYSEC-2026-1563

Denial of Service (DoS) in run-llama/llama_index

Published Mar 20, 2025 · Updated Oct 15, 2025 · Assigned by @huntr_ai

Description

A vulnerability in the LangChainLLM class of the run-llama/llama_index repository, version v0.12.5, allows for a Denial of Service (DoS) attack. The stream_complete method executes the llm using a thread and retrieves the result via the get_response_gen method of the StreamingGeneratorCallbackHandler class. If the thread terminates abnormally before the _llm.predict is executed, there is no exception handling for this case, leading to an infinite loop in the get_response_gen function. This can be triggered by providing an input of an incorrect type, causing the thread to terminate and the process to continue running indefinitely.

Affected products

VendorProductAffectedFixed
run-llama run-llama/llama_index unspecified – < 0.12.6 0.12.6

Affected packages

EcosystemPackageAffectedFixedRecord
PyPI llama-index <= 0.12.5 — PYSEC-2025-244
PyPI llama-index-core < 0.12.6 0.12.6 GHSA-j3wr-m6xh-64hg

References