What’s Vulnerable › Vulnerabilities

CVE-2025-3044: MD5 Hash Collision in run-llama/llama_index

• Severity: medium (CVSS 5.3 v3.0)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.3% probability of exploitation in the next 30 days
• Public exploit or detection template: yes
• Published: 2025-07-07 · updated 2026-06-17
• Weakness: CWE-440

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.

Affected products

• run-llama/llama_index: before 0.12.28 — fixed in 0.12.28

How to fix

Upgrade to a fixed version: run-llama/llama_index 0.12.28. Check the vendor advisory for mitigations.

References

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

Get alerted when CVE-2025-3044 or the next vulnerability affects your stack