CVE-2025-6211 | MD5 Hash Collision in run-llama/llama_index

Exp

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.

Published: 2025-07-10 Last update: 2025-07-30 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2025-6211 is rated Exploit Available (59.9/100): CVSS Medium severity, with medium exploitation likelihood (EPSS 0.30%). 1 public exploit reference(s) are indexed (Exploit-DB). Public exploits are available—assess exposure, apply mitigations, and prioritize patching.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Public exploit references (Exploit-DB) for CVE-2025-6211

EDB-ID Source Kind Published Link
— nvd_ref exploit_tag Exploit-DB ↗

Exploit prediction scoring system (EPSS) score for CVE-2025-6211

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-05-06 0.07% 0.30% +0.24%
2 2025-08-21 0.04% 0.07% +0.03%
3 2025-07-11 — 0.04% —

Full EPSS history (3 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2025-6211

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
6.5 3.0 MEDIUM
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:N)
Doesn’t really leak secrets in a meaningful way.
Integrity (I:L)
Attackers could change some data, but it’s limited—not everything goes.
Availability (A:L)
Might cause slowdowns, glitches, or partial disruption—not a full brick.
 3.9 2.5 [email protected]

Weakness enumeration for CVE-2025-6211

GitHub Security Advisory for CVE-2025-6211

GHSA-5hq9-5r78-2gjh · Severity: medium · Ecosystem: pip — LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class

OS Trackers for CVE-2025-6211

vendor priority summary link
redhat medium — https://access.redhat.com/security/cve/CVE-2025-6211

Affected software / configurations for CVE-2025-6211

Vendor Product Version Raw CPE
llamaindex llamaindex < 0.3.1 cpe:2.3:a:llamaindex:llamaindex:*:*:*:*:*:*:*:*

References for CVE-2025-6211

cvelogic Threat Intelligence