# LlamaIndex (run-llama/llama_index) versions up to and including 0.11.6 contain an unsafe deserialization vulnerability in BGEM3Index.load_from_disk() in llama_index/indices/managed/bge_m3/base.py. ...

Advisory record · `PYSEC-2026-85`

- **Identifiers:** `PYSEC-2026-85` · `CVE-2024-14021`
- **State:** Confirmed
- **Severity:** CVSS 8.4 High
- **Critical:** No
- **Weakness (CWE):** [CWE-502](https://cwe.mitre.org/data/definitions/502.html)
- **Tags:** [Insecure deserialization](https://agentprime.io/advisories/tag/deserialization.md)
- **Published:** 12 Jan 2026
- **Updated:** 20 May 2026
- **Reviewed by a person:** No

Published by OSV at 12 Jan 2026, 23:15 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `llama-index` (PyPI): affected `<0.11.7`; fixed in `0.11.7`

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 8.4 High, CVSS 4.0: `CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N`, from CNA (VulnCheck)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0034, the 27th percentile, on 12 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

This record came from the full history of OSV, published 12 Jan 2026. New records show when each source confirmed them.

## Sources

- [OSV: PYSEC-2026-85](https://osv.dev/vulnerability/PYSEC-2026-85)
- <https://www.llamaindex.ai/>
- <https://www.vulncheck.com/advisories/llamaindex-bgem3index-unsafe-deserialization>
- <https://github.com/run-llama/llama_index>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/PYSEC-2026-85>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/PYSEC-2026-85/>. Everything for agents: <https://agentprime.io/llms.txt>.