CVE-2025-6211
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.
Does this matter?
Lower severity and a low EPSS score (0.32%). Track it; it rarely justifies an emergency change on its own.
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.
- CVSS 3.0
- 6.5 MEDIUMCVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L
- EPSS
- 0.32% probability · 24th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-440
- Affected
- llamaindex/llamaindex
- Source
- security@huntr.dev
References
- https://github.com/run-llama/llama_index/commit/29b2e07e64ed7d302b1cc058185560b28eaa1352Patch
- https://huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389Exploit, Third Party Advisory
- https://huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389Exploit, Third Party Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.