CVE-2024-12704: LangChainLLM denial of service through infinite loop in stream_complete

Summary

CVE-2024-12704 affects the LangChainLLM class in the run-llama/llama_index repository, version v0.12.5. The stream_complete method runs the llm in a thread and reads the result through get_response_gen of StreamingGeneratorCallbackHandler. If the thread terminates abnormally before _llm.predict executes, get_response_gen enters an infinite loop because no exception handling covers this case. Providing an input of an incorrect type triggers this, enabling a Denial of Service (DoS) attack.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

• llama-index-corePyPILLM dependency since 2024-02-02 · 34 tracked dependents

Related items

• LowCloakFEM: Agentic FEM Code Generation for Red-Teaming Computational Resource ExhaustionSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• MediumThe Rise of LLMJacking: How Threat Actors Monetize Compromised Cloud and Model ResourcesSimilar attack · Google Threat Intelligence
• InfoThe Blind Spots of Detection: Adversarial Perturbation Attacks against Watchdogs in Distributed LLM InferenceSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• HighCVE-2026-118761: Kubeflow Pipelines decompression bomb in pipeline archive uploadSimilar attack · NVD/CVE Database
• LowOpenCode User Hit with Hostile Backlash After Reporting Free AI LoopholeSimilar attack · Socket Blog