Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍 PyPI

CVE-2025-6211

MEDIUM

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

Also known asGHSA-5hq9-5r78-2gjh
Published
Jul 10, 2025
Updated
Apr 10, 2026
Affected
2 pkgs
Patched
2 / 2
Exploits
None indexed

EPSS Exploitation Probability

via FIRST.org ↗
0.3%probability of exploitation in next 30 days
Lower Risk23th percentile+0.01%
0.00%0.27%0.54%0.81%0.1%0.3%Dec 25Apr 26Jun 26

EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.

Blast Radius

2 pkgs affected
🐍llama-index🐍llama-index-readers-docugami

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

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.

Affected Packages

2 total 2 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIllama-indexall versions0.12.41
🐍PyPIllama-index-readers-docugamiall versions0.3.1

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for llama-index. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.

  2. Fix

    Update llama-index to 0.12.41 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2025-6211 is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

  4. How O3 protects you

    O3 pinpoints whether CVE-2025-6211 is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Tailored to CVE-2025-6211. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

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.
O3 Security · Impact-Aware SCA

Is CVE-2025-6211 in your dependencies?

O3 detects CVE-2025-6211 across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.