Vulnerability · Published Mar 20, 2025 · Assigned by @huntr_ai
CVE-2024-12704Denial of Service (DoS) in run-llama/llama_index
High 7.5
In plain English
A high-severity infinite loop in run-llama/llama_index from run-llama. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.8% (higher than 58% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official 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 packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | llama-index | no fix listed | PYSEC-2025-244 |
| PyPI | llama-index-core | 0.12.6 | GHSA-j3wr-m6xh-64hg |
| PyPI | llama-index-core | 0.12.6 | PYSEC-2026-1563 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| run-llama | run-llama/llama_index | unspecified – before 0.12.6 |
Weakness: CWE-835 · Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H