CVE-2025-6211
mediumPriorität · verfolgen · 0EPSS 0.004 · 29. PerzentilEUUSEPSS · bewertet 2026-10-24
A vulnerability in the DocugamiReader class of the run-llama/llama_index repository, up to version 0.12.28, involves the use of MD5 hashing to generate IDs for document chunks. This approach leads to hash collisions when structurally distinct chunks contain identical text, resulting in one chunk overwriting another. This can cause loss of semantically or legally important document content, breakage of parent-child chunk hierarchies, and inaccurate or hallucinated responses in AI outputs. The issue is resolved in version 0.3.1.
cvss
Technischer Schweregrad, 0–10. Eine Zeile je Quelle.
Basiswert 0–10 · höher = schwerwiegender · Vektor überfahren zum Auflösen
SSVC
Eine Handlungsentscheidung — aus Ausnutzung und Auswirkung.
schwächen
Die CWE-Schwächeklassen, zu denen dies gehört.
betroffene Produkte (4)
Betroffene Produkte und Versionsbereiche.
Advisories (3)
Hersteller- und Ökosystem-Meldungen dazu.
- GHSA-5hq9-5r78-2gjhLlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class 2025-07-10ghsa · osvUS
A vulnerability in the DocugamiReader class of the run-llama/llama_index repository, up to but excluding version 0.12.41, involves the use of MD5 hashing to generate IDs for document chunks. This approach leads to hash collisions when structurally distinct chunks contain identical text, resulting in one chunk overwriting another. This can cause loss of semantically or legally important document content, breakage of parent-child chunk hierarchies, and inaccurate or hallucinated responses in AI outputs. The issue is resolved in version 0.3.1.
- PYSEC-2026-1566LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class 2026-07-07vendor · osvUS
A vulnerability in the DocugamiReader class of the run-llama/llama_index repository, up to but excluding version 0.12.41, involves the use of MD5 hashing to generate IDs for document chunks. This approach leads to hash collisions when structurally distinct chunks contain identical text, resulting in one chunk overwriting another. This can cause loss of semantically or legally important document content, breakage of parent-child chunk hierarchies, and inaccurate or hallucinated responses in AI outputs. The issue is resolved in version 0.3.1.
- PYSEC-2026-2606LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class 2026-07-13vendor · osvUS
A vulnerability in the DocugamiReader class of the run-llama/llama_index repository, up to but excluding version 0.12.41, involves the use of MD5 hashing to generate IDs for document chunks. This approach leads to hash collisions when structurally distinct chunks contain identical text, resulting in one chunk overwriting another. This can cause loss of semantically or legally important document content, breakage of parent-child chunk hierarchies, and inaccurate or hallucinated responses in AI outputs. The issue is resolved in version 0.3.1.
auch bekannt als (8)
Weitere Namen und Kennungen dieser Entität.
quellen
Welche Quellen diesen Datensatz belegen und wann.
Referenzen (8)
Externe Belege — Patches, Meldungen, Analysen.
- https://github.com/run-llama/llama_index/commit/29b2e07e64ed7d302b1cc058185560b28eaa1352cnnvd
- https://github.com/run-llama/llama_index/releasesPatchcnnvd
- https://huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389cnnvd
- https://nvd.nist.gov/vuln/detail/CVE-2025-6211cnnvd
- https://github.com/run-llama/llama_index/commit/29b2e07e64ed7d302b1cc058185560b28eaa1352enisa_euvd
- https://huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389enisa_euvd
- https://github.com/run-llama/llama_index/commit/29b2e07e64ed7d302b1cc058185560b28eaa1352Patchnvd
- https://huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389ExploitThird Party Advisorynvd
Angreifer nutzen Schwachstellen wie diese gegen im Internet exponierte Dienste aus. Sehen Sie mit einem kostenlosen Passiv-Scan, was exponiert ist.
Kostenloser Scan