GHSA-5hq9-5r78-2gjh: LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class

1. GitHub Advisory Database
2. GitHub Reviewed
3. CVE-2025-6211

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

Package

pip llama-index (pip)

Affected versions

< 0.12.41

pip llama-index-readers-docugami (pip)

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

• https://nvd.nist.gov/vuln/detail/CVE-2025-6211
• run-llama/llama_index@29b2e07
• https://huntr.com/bounties/1a48a011-a3c5-4979-9ffc-9652280bc389

Published to the GitHub Advisory Database

Jul 10, 2025

Last updated

Jul 10, 2025