PYSEC-2026-1563
Vulnerability from pysec - Published: 2026-07-07 14:34 - Updated: 2026-07-07 17:24A 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.
| Name | purl | llama-index-core | pkg:pypi/llama-index-core |
|---|
{
"affected": [
{
"package": {
"ecosystem": "PyPI",
"name": "llama-index-core",
"purl": "pkg:pypi/llama-index-core"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "0.12.6"
}
],
"type": "ECOSYSTEM"
}
],
"versions": [
"0.10.0",
"0.10.1",
"0.10.10",
"0.10.11",
"0.10.11.post1",
"0.10.12",
"0.10.13",
"0.10.14",
"0.10.14.post1",
"0.10.15",
"0.10.16",
"0.10.16.post1",
"0.10.17",
"0.10.18",
"0.10.18.post1",
"0.10.19",
"0.10.2",
"0.10.20",
"0.10.20.post1",
"0.10.20.post2",
"0.10.20.post3",
"0.10.21",
"0.10.21.post1",
"0.10.22",
"0.10.23",
"0.10.23.post1",
"0.10.24",
"0.10.24.post1",
"0.10.24a1",
"0.10.25",
"0.10.25.post1",
"0.10.25.post2",
"0.10.25.post3",
"0.10.25a1",
"0.10.26",
"0.10.27",
"0.10.28",
"0.10.29",
"0.10.3",
"0.10.30",
"0.10.31",
"0.10.32",
"0.10.33",
"0.10.34",
"0.10.35",
"0.10.35.post1",
"0.10.36",
"0.10.37",
"0.10.37.post1",
"0.10.38",
"0.10.38.post1",
"0.10.38.post2",
"0.10.39",
"0.10.39.post1",
"0.10.40",
"0.10.41",
"0.10.42",
"0.10.43",
"0.10.43.post1",
"0.10.44",
"0.10.45",
"0.10.46",
"0.10.47",
"0.10.48",
"0.10.48.post1",
"0.10.49",
"0.10.5",
"0.10.50",
"0.10.50.post1",
"0.10.51",
"0.10.52",
"0.10.52.post1",
"0.10.52.post2",
"0.10.53",
"0.10.53.post1",
"0.10.54",
"0.10.54.post1",
"0.10.55",
"0.10.56",
"0.10.57",
"0.10.58",
"0.10.59",
"0.10.59a1",
"0.10.59a2",
"0.10.5a1",
"0.10.5a10",
"0.10.5a2",
"0.10.5a3",
"0.10.5a4",
"0.10.5a5",
"0.10.5a6",
"0.10.5a7",
"0.10.5a8",
"0.10.5a9",
"0.10.6",
"0.10.6.post1",
"0.10.60",
"0.10.61",
"0.10.62",
"0.10.63",
"0.10.64",
"0.10.65",
"0.10.66",
"0.10.67",
"0.10.68",
"0.10.68.post1",
"0.10.7",
"0.10.8",
"0.10.8.post1",
"0.10.9",
"0.11.0",
"0.11.0.post1",
"0.11.1",
"0.11.10",
"0.11.11",
"0.11.12",
"0.11.13",
"0.11.13.post1",
"0.11.14",
"0.11.15",
"0.11.16",
"0.11.17",
"0.11.18",
"0.11.19",
"0.11.2",
"0.11.20",
"0.11.21",
"0.11.22",
"0.11.23",
"0.11.3",
"0.11.4",
"0.11.5",
"0.11.6",
"0.11.7",
"0.11.8",
"0.11.9",
"0.12.0",
"0.12.1",
"0.12.2",
"0.12.3",
"0.12.4",
"0.12.5",
"0.9.41",
"0.9.42",
"0.9.42.post3",
"0.9.43",
"0.9.44",
"0.9.44.post1",
"0.9.44.post2",
"0.9.44.post3",
"0.9.45",
"0.9.46",
"0.9.47",
"0.9.48",
"0.9.49",
"0.9.50",
"0.9.50.post1",
"0.9.51",
"0.9.52",
"0.9.53",
"0.9.54",
"0.9.55",
"0.9.56"
]
}
],
"aliases": [
"CVE-2024-12704",
"GHSA-j3wr-m6xh-64hg"
],
"details": "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.",
"id": "PYSEC-2026-1563",
"modified": "2026-07-07T17:24:33.536350Z",
"published": "2026-07-07T14:34:53.244852Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2024-12704"
},
{
"type": "WEB",
"url": "https://github.com/run-llama/llama_index/commit/d1ecfb77578d089cbe66728f18f635c09aa32a05"
},
{
"type": "PACKAGE",
"url": "https://github.com/run-llama/llama_index"
},
{
"type": "WEB",
"url": "https://huntr.com/bounties/a0b638fd-21c6-4ba7-b381-6ab98472a02a"
},
{
"type": "PACKAGE",
"url": "https://pypi.org/project/llama-index-core"
},
{
"type": "ADVISORY",
"url": "https://github.com/advisories/GHSA-j3wr-m6xh-64hg"
}
],
"severity": [
{
"score": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
"type": "CVSS_V3"
}
],
"summary": "LlamaIndex Improper Handling of Exceptional Conditions vulnerability"
}
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.