Vulnerability 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.
CVSS Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Llamaindex | Llamaindex | 0.12.5 |
Related Weaknesses (CWE)
References
- https://github.com/run-llama/llama_index/commit/d1ecfb77578d089cbe66728f18f635c0Patch
- https://huntr.com/bounties/a0b638fd-21c6-4ba7-b381-6ab98472a02aExploitThird Party Advisory
FAQ
What is CVE-2024-12704?
CVE-2024-12704 is a vulnerability with a CVSS score of 7.5 (HIGH). 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 thr...
How severe is CVE-2024-12704?
CVE-2024-12704 has been rated HIGH with a CVSS base score of 7.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2024-12704?
Check the references section above for vendor advisories and patch information. Affected products include: Llamaindex Llamaindex.