Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · LlamaIndex

CVE-2025-6211: LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class

mediumCVSS 3.0 6.5GHSA-5hq9-5r78-2gjh

A vulnerability in the DocugamiReader class of the run-llama/llamaindex 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.

Published Jul 10, 2025

Affected packages

llama-index

Ecosystem
PyPI
Affected
< 0.12.41
Fixed in
0.12.41
Check
pip show llama-index

llama-index-readers-docugami

Ecosystem
PyPI
Affected
< 0.3.1
Fixed in
0.3.1
Check
pip show llama-index-readers-docugami

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

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.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More LlamaIndex vulnerabilities

All LlamaIndex entries