Home

Description

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.

PUBLISHED Reserved 2025-06-17 | Published 2025-07-10 | Updated 2025-07-10 | Assigner @huntr_ai




MEDIUM: 6.5CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L

Problem types

CWE-440 Expected Behavior Violation

Product status

Any version before 0.3.1
affected

References

huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389 exploit

huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389

github.com/...ommit/29b2e07e64ed7d302b1cc058185560b28eaa1352

cve.org (CVE-2025-6211)

nvd.nist.gov (CVE-2025-6211)

Download JSON