Skip to content
Fencer Vulns
high 7.5

CVE-2024-12704 json

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

published 2025-03-20 19 mo ago modified 2026-07-13 3 mo ago also GHSA-j3wr-m6xh-64hg , PYSEC-2025-244 , PYSEC-2026-1563 , EUVD-2025-7006

cvss
7.5
version 3.0, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.8%
EPSS 0.8% chance of exploitation in 30 days, percentile 57%
public exploits
0
none known

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.

Patch / fix

  • pypi llama-index-core 0.12.6
  • run-llama run-llama/llama_index 0.12.6

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2024-12704 updated cvss 7.5

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

  • Red Hat OpenShift Lightspeed openshift-lightspeed-tech-preview/lightspeed-service-api-rhel9
    affected: workaround, no fix available

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
Proof of concept is public
Automatable
yes
Technical impact
partial
Assessed
19 mo ago

Exploit prediction

0.83% chance of exploitation in the next 30 days, higher than 57% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • huntr.com https://huntr.com/bounties/a0b638fd-21c6-4ba7-b381-6ab98472a02a referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.0 7.5 CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
GitHub 3.0 7.5 CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
OSV 3.0 7.5 CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Affected packages

ecosystem package affected fixed in
pypi llama-index-core
<0.12.6
0.12.6
pypi llama-index
<=0.12.5
 no fix listed

Affected products

  • run-llama run-llama/llama_index

Classification

Weakness
  • CWE-835 Loop with Unreachable Exit Condition
  • CWE-755 Improper Handling of Exceptional Conditions

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.