LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class

TRUNG BÌNH 6.5CVE-2025-6211 · GHSA-5hq9-5r78-2gjh · PYSEC-2026-1566 · Công bố 10/07/2025 · cập nhật 17/06/2026

Tóm tắt nhanh

CVE-2025-6211 là lỗ hổng mức TRUNG BÌNH (CVSS 6.5) ảnh hưởng llama-index, llama-index-readers-docugami, llamaindex (llamaindex).
Xác suất bị khai thác trong 30 ngày tới (EPSS): 0.36%, cao hơn 29.9% các lỗ hổng khác.
Cách xử lý: cập nhật lên 0.12.41, 0.3.1 hoặc mới hơn.

Gói / sản phẩm	Phiên bản bị ảnh hưởng	Phiên bản đã vá
llama-index PyPI	`< 0.12.41`	`0.12.41`
llama-index-readers-docugami PyPI	`< 0.3.1`	`0.3.1`
llamaindex llamaindex	`< 0.3.1`	`0.3.1`

Mô tả

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.

Mô tả của NVD

A vulnerability in the DocugamiReader class of the run-llama/llama_index repository, up to version 0.12.28, 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.