{"answers":{"affected":"6 open source packages ship an affected version, including llama-index and llama-index-readers-docugami. It affects 1 product.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-6211 exists.","fix":"Upgrade llama-index to 0.12.41 or later.","what":"CVE-2025-6211 is a medium-severity vulnerability in run-llama/llama_index, published on 10 Jul 2025. An attacker can exploit it over the internet without logging in, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2025-6211 and fix it if it is affected.\n\nWhat it is: CVE-2025-6211 is a medium-severity vulnerability in run-llama/llama_index, published on 10 Jul 2025. An attacker can exploit it over the internet without logging in, with no action from the victim.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-6211 exists.\n\nAffected packages and fixed versions:\n- llama-index (PyPI): affected all versions; fixed in 0.12.41\n- llama-index (PyPI): affected all versions; fixed in 0.12.41\n- llama-index (PyPI): affected all versions; fixed in 0.12.41\n- llama-index-readers-docugami (PyPI): affected all versions; fixed in 0.3.1\n- llama-index-readers-docugami (PyPI): affected all versions; fixed in 0.3.1\n- llama-index-readers-docugami (PyPI): affected all versions; fixed in 0.3.1\n\nTask:\n1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.\n2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.\n3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.\n4. Run the tests and summarise what changed and why.\n5. If nothing in the project is affected, say so and change nothing.\n\nReference: https://insights.sbomify.com/CVE-2025-6211/ (Markdown: https://insights.sbomify.com/CVE-2025-6211/index.md)","id":"CVE-2025-6211","markdown":"https://insights.sbomify.com/CVE-2025-6211/index.md","name":"CVE-2025-6211","record":{"aliases":["GHSA-5hq9-5r78-2gjh","PYSEC-2026-1566","PYSEC-2026-2606"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["data_modify","other"],"network_reachable":"yes","non_default_config":false,"product_category":"Python AI library","requires_auth":"none","summary":"Attackers can cause data loss and AI hallucinations in llama_index by exploiting MD5 hash collisions in document chunking.","user_interaction":"not_required","vuln_class":"other"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"@huntr_ai","cpe":[{"product":"llamaindex","vendor":"llamaindex"}],"cvss":{"score":6.5,"severity":"medium","source":"cna","vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:L","version":"3.0"},"cwes":[{"id":"CWE-440","name":"Expected Behavior Violation"}],"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.","ecosystems":["PyPI"],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"weaponised"},"has_fix":true,"headline":"MD5 Hash Collision in run-llama/llama_index","id":"CVE-2025-6211","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"other","year":"2025"},"n_packages":6,"n_references":2,"next":{"headline":"Ultra Addons for Contact Form 7 3.5.11 - 3.5.19 - Unauthenticated Stored Cross-Site Scripting via Database module","id":"CVE-2025-6212"},"packages":[{"ecosystem":"PyPI","fixed":["0.12.41"],"introduced":["0"],"last_affected":[],"package":"llama-index","purl":null,"source":"GHSA-5hq9-5r78-2gjh"},{"ecosystem":"PyPI","fixed":["0.12.41"],"introduced":["0"],"last_affected":[],"package":"llama-index","purl":"pkg:pypi/llama-index","source":"GHSA-5hq9-5r78-2gjh"},{"ecosystem":"PyPI","fixed":["0.12.41"],"introduced":["0"],"last_affected":[],"package":"llama-index","purl":"pkg:pypi/llama-index","source":"PYSEC-2026-2606"},{"ecosystem":"PyPI","fixed":["0.3.1"],"introduced":["0"],"last_affected":[],"package":"llama-index-readers-docugami","purl":null,"source":"GHSA-5hq9-5r78-2gjh"},{"ecosystem":"PyPI","fixed":["0.3.1"],"introduced":["0"],"last_affected":[],"package":"llama-index-readers-docugami","purl":"pkg:pypi/llama-index-readers-docugami","source":"GHSA-5hq9-5r78-2gjh"},{"ecosystem":"PyPI","fixed":["0.3.1"],"introduced":["0"],"last_affected":[],"package":"llama-index-readers-docugami","purl":"pkg:pypi/llama-index-readers-docugami","source":"PYSEC-2026-1566"}],"prev":{"headline":"Hardlink-Based Path Traversal in run-llama/llama_index","id":"CVE-2025-6210"},"products":["run-llama/llama_index"],"published":"2025-07-10","related":[{"cvss_score":10,"headline":"SQL Injection to RCE in run-llama/llama_index","id":"CVE-2024-12909","kev_date_added":null,"published":"2025-03-20"},{"cvss_score":9.8,"headline":"SQL Injection in run-llama/llama_index","id":"CVE-2025-1793","kev_date_added":null,"published":"2025-06-05"},{"cvss_score":9.8,"headline":"SQL Injection in run-llama/llama_index","id":"CVE-2025-1750","kev_date_added":null,"published":"2025-06-02"},{"cvss_score":9.8,"headline":"SQL Injection in run-llama/llama_index","id":"CVE-2024-11958","kev_date_added":null,"published":"2025-03-20"},{"cvss_score":9.8,"headline":"Command Injection in run-llama/llama_index","id":"CVE-2024-3271","kev_date_added":null,"published":"2024-04-16"},{"cvss_score":9.8,"headline":"SQL injection in llama-index","id":"CVE-2024-23751","kev_date_added":null,"published":"2024-01-22"},{"cvss_score":8.8,"headline":"LlamaIndex includes an exec call for `import {cls_name}`","id":"CVE-2024-45201","kev_date_added":null,"published":"2024-08-22"}],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"CC BY 4.0","name":"GitHub Advisory Database","prefix":"GHSA"},{"class":"attribution","licence":"CC BY 4.0","name":"PyPA Advisory Database","prefix":"PYSEC"},{"class":"attribution","licence":"US public information, NVD API terms","name":"NVD"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"}],"ssvc":{"automatable":"yes","exploitation":"poc","technical_impact":"partial"},"state":"PUBLISHED","updated":"2025-07-10","vendors":["run-llama"]},"summary":"Attackers can cause data loss and AI hallucinations in llama_index by exploiting MD5 hash collisions in document chunking.","url":"https://insights.sbomify.com/CVE-2025-6211/"}