llama-index
Affected
- introduced
0, last affected0.12.5(ecosystem)
Fixed versions
None listed
Fix
No fixed version is listed.
Advisory
Also known as: CVE-2024-12704, GHSA-j3wr-m6xh-64hg, PYSEC-2026-1563
The record has no summary.
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.
High Basis: CVSS v3 score 7.5, vector CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
0, last affected 0.12.5 (ecosystem)None listed
No fixed version is listed.
Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: PyPA Advisory Database · CC BY 4.0