CVE-2025-6211
mediumpriority · track · 0EPSS 0.004 · 29 %ileEUUSEPSS · scored 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
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
affected products (4)
Products and version ranges known to be affected.
advisories (3)
Vendor and ecosystem advisories describing this.
- 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.
also known as (8)
Other names and identifiers for this entity.
sources
Which sources assert this record, and when.
references (8)
External citations — patches, advisories, analysis.
- 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
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan