AI and data stack advisories

Severe, 6 weeks1496Projects326

1496 severe, 6 weeks · 326 projects

LlamaIndexPYSEC-2025-247

A vulnerability in the ArxivReader class of the run-llama/llama_index repository

LlamaIndex

CVE-2025-3044 · Published Jul 7, 2025 · updated Jul 13, 2026

Medium5.3
Fix: upgrade to 0.12.28 or later
Source advisory

A vulnerability in the ArxivReader class of the run-llama/llama_index repository, versions up to v0.12.22.post1, allows for MD5 hash collisions when generating filenames for downloaded papers. This can lead to data loss as papers with identical titles but different contents may overwrite each other, preventing some papers from being processed for AI model training. The issue is resolved in version 0.12.28.

Affected versions

PackageAffectedFixed in
llama-index
PyPI
< 0.12.280.12.28
Details and references
CVSS 3.0
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N
Severity from
the CVSS score
Also known as
CVE-2025-3044, GHSA-p7j4-jwjf-5x9w, PYSEC-2026-1569

More LlamaIndex advisories

All LlamaIndex