# llama-index-core Command Injection vulnerability

Advisory record · `GHSA-r6gp-rff2-p3hf`

- **Identifiers:** `GHSA-r6gp-rff2-p3hf` · `CVE-2024-3271` · `PYSEC-2026-396`
- **State:** Confirmed
- **Severity:** CVSS 9.8 Critical
- **Critical:** Yes: CVSS 9+
- **Weakness (CWE):** [CWE-77](https://cwe.mitre.org/data/definitions/77.html)
- **Tags:** [Command injection](https://agentprime.io/advisories/tag/command-injection.md)
- **Published:** 29 Jun 2026
- **Updated:** 1 Jul 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 29 Jun 2026, 11:50 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Critical

Critical, because:

- CVSS score 9.8: 9.0 or more.

How we decide what’s critical: <https://agentprime.io/advisories/critical.md>

## Affected packages

- `llama-index-core` (PyPI): affected `<0.10.24`; fixed in `0.10.24`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> llama-index-core versions before 0.10.24 are vulnerable to command injection in the safe_eval function, which is meant to block code generated by an LLM that contains underscores. An attacker who can supply input that the LLM turns into code can craft it to avoid the underscore check and run arbitrary OS commands on the server, giving remote code execution. Upgrade llama-index-core to version 0.10.24 or later.

Written 10 Nov 2026.

## 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

- 9.8 Critical, CVSS 3.0: `CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`, from CNA (@huntr_ai)

- **CISA KEV:** Not listed.
- **EPSS:** 0.029, the 87th percentile, on 14 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

This record came from the full history of the GitHub Advisory Database, published 29 Jun 2026. New records show when each source confirmed them.

## Sources

- [GitHub Advisory Database: GHSA-r6gp-rff2-p3hf](https://github.com/advisories/GHSA-r6gp-rff2-p3hf)
- [OSV: GHSA-r6gp-rff2-p3hf](https://osv.dev/vulnerability/GHSA-r6gp-rff2-p3hf)
- <https://nvd.nist.gov/vuln/detail/CVE-2024-3271>
- <https://github.com/run-llama/llama_index/commit/2c92e88838a5f481d50840240b1dd3180066c6f5>
- <https://github.com/run-llama/llama_index/commit/5fbcb5a8b9f20f81b791c7fc8849e352613ab475>
- <https://github.com/run-llama/llama_index>
- <https://huntr.com/bounties/9b32490e-7cf9-470e-8d49-ba083ae7a279>
- <https://pypi.org/project/llama-index-core>
- <https://github.com/advisories/GHSA-r6gp-rff2-p3hf>

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/GHSA-r6gp-rff2-p3hf>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-r6gp-rff2-p3hf/>. Everything for agents: <https://agentprime.io/llms.txt>.