LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class
Moderate severity
GitHub Reviewed
Published
Jul 10, 2025
to the GitHub Advisory Database
•
Updated Jul 10, 2025
Description
Published by the National Vulnerability Database
Jul 10, 2025
Published to the GitHub Advisory Database
Jul 10, 2025
Reviewed
Jul 10, 2025
Last updated
Jul 10, 2025
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