Read the docs
TI-2024-11778 Aliases CVE-2024-12704GHSA-j3wr-m6xh-64hg

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

Priority HIGH 72CWE-835Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
Low
Impact type
Denial of service
Confidentiality · integrity · availability
None · None · High
Fix status
Partial Red Hat: 1 without a fix

Attack profile from CVSS 3.0 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-835.

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.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00831 57th percentileScored 2026-11-07
Public exploit Yes 1 exploit referenceTagged by NVD
Fix Partial run-llama/llama_index (run-llama): 0.12.6llama-index-core (PyPI): 0.12.6Red Hat: 1 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Poc
Automatable
Yes
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
run-llamarun-llama/llama_indexbefore 0.12.60.12.6Patch availableCNA
—llama-index-core (PyPI)before 0.12.60.12.6Patch availableGHSA-j3wr-m6xh-64hg
  • run-llama/llama_index Vendorrun-llama Affected before 0.12.6 Fixed in 0.12.6 Patch available CNA
  • llama-index-core (PyPI) Vendor— Affected before 0.12.6 Fixed in 0.12.6 Patch available GHSA-j3wr-m6xh-64hg

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:llamaindex:llamaindex:0.12.5:*:*:*:*:*:*:*0.12.5Vulnerablerun-llama
  • cpe:2.3:a:llamaindex:llamaindex:0.12.5:*:*:*:*:*:*:* Versions 0.12.5 Vulnerable ·run-llama

Remediation

  • Fix · CNA run-llama/llama_index (run-llama) Fixed in 0.12.6
  • Fix · GHSA-j3wr-m6xh-64hg llama-index-core (PyPI) Fixed in 0.12.6 Advisory →

Vendor assessments

Red Hat

Red Hat rating: Important. Red Hat's page for this CVE →

ProductStatusPlan or fix
OpenShift LightspeedAffectedNo fix yet

Timeline

  1. 2026-10-02 Threatist record created from CVE-2024-12704
  2. 2026-10-03 Alias added: GHSA-j3wr-m6xh-64hg

References

Exploit 1

Patch 1

Advisory 1

Other 1

  • TI-2025-01545 SQL Injection in run-llama/llama_index CVSS 3.0CRITICAL 9.8
  • TI-2025-01507 SQL Injection in run-llama/llama_index CVSS 3.0CRITICAL 9.8
  • TI-2024-11960 SQL Injection to RCE in run-llama/llama_index CVSS 3.1CRITICAL 9.8
  • TI-2024-11094 SQL Injection in run-llama/llama_index CVSS 3.0CRITICAL 9.8
  • TI-2024-03068 Command Injection in run-llama/llama_index CVSS 3.0CRITICAL 9.8
  • TI-2024-15754 LlamaIndex (aka llama_index) through 0.9.34 allows SQL injection via the Text-to-SQL… CVSS 3.1CRITICAL 9.8
See all 23 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences