Skip to main content
Public proof of conceptFix available

CVE-2024-12704

A public proof of concept exists; no exploitation attested.

  • Published2025-03-20
  • WeaknessCWE-835

Am I affected?

With a domain, we read the version its public headers and pages expose. A distribution build can carry the fix under an older number.

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.

Timeline

dates in UTC
  1. 2025-03-2010:15CVE publishedNVD

Versions per branch

OSV · NVD
llama-index
BranchAffectedFixed in
0.12≤ 0.12.5no fix published
Llamaindex
BranchAffectedFixed in
0.12= 0.12.5no fix published
llama-index-core
BranchAffectedFixed in
0.12< 0.12.60.12.6

as publishedRanges as NVD and OSV publish them; a distribution’s build can be fixed under an older number.

Products declared by the CNA1 product

As @huntr_ai, the CNA that assigned this CVE, declared them in the CVE record; versions as written.

  • run-llama/llama_index
    Affected
    • < 0.12.6fixed in 0.12.6custom

Source: the CNA record (CVE Program), © The MITRE Corporation,CVE Terms of UseCVE recordupdated 2025-10-15

Distribution builds and vendor advisories

Packages from OSV.dev and products from the vendors' CSAF advisories.

version not verifiedVersions not verified: read as OSV.dev and the vendors publish them, not checked against each vendor's release list.

Vendor advisories

  • CVE-2024-12704 Red Hat Product Security1 known affected

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

    openshift-lightspeed-tech-preview/lightspeed-service-api-rhel9 as a component of OpenShift Lightspeed

Full record on NVD

Fix

  1. Workaround from the vendor Red Hat Product Security CVE-2024-12704 · 1 productMitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base or stability.
  2. No fix available, says the vendor Red Hat Product Security CVE-2024-12704 · 1 productAffected

Advisories and patches

Detection

Nuclei template
none so far
ProjectDiscovery
Exploit-DB
no entry
Exploit-DB
Proof of concept
Metasploit modules
none listed
Metasploit Framework

Sources

  • NVDCVE recordread 2026-10-23
  • CISA-ADPSSVC decisionpoc2025-03-20
  • CNACVSS 3.07.5known since 2026-10-23
  • CNAweakness (CWE)CWE-835known since 2026-10-23
  • FIRST EPSSEPSS score0.8 %2026-11-18
  • OSVaffected packages—
  • GitHub AdvisoriesadvisoryHIGH2025-03-21

Identifiers

Technical details

CVSS v3 Vector
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Published
2025-03-20
Last Modified
2026-06-17
NVD status
Modified
GitHub Advisory
GHSA-j3wr-m6xh-64hg

Frequently asked questions

What is CVE-2024-12704?

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.

Is CVE-2024-12704 actively exploited?

A proof-of-concept exploit exists for CVE-2024-12704, but active exploitation has not been confirmed at this time.

What is the CVSS score for CVE-2024-12704?

CVE-2024-12704 has a CVSS v3 base score of 7.5 (HIGH severity), with vector string CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H.

Running llama-index? Hear about its next vulnerability

Surveillance reads the versions in your stack — a domain, a lockfile or a list — checks each CVE against the ranges its sources publish, and alerts you when one you run is exploited or enters CISA KEV. A version it cannot read stays « version not verified ».

No credit card required · No monthly cap on website lookups · 250 API requests/month

Sources for this record