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

CVE-2024-4181

HIGH

RunGptLLM class in LlamaIndex has a command injection

Also known asGHSA-pw38-xv9x-h8ch
Published
May 16, 2024
Updated
Mar 14, 2026
Affected
2 pkgs
Patched
2 / 2
Exploits
None indexed

EPSS Exploitation Probability

via FIRST.org ↗
2.1%probability of exploitation in next 30 days
Lower Risk79th percentile+0.50%
1.11%1.62%2.12%2.62%1.6%2.1%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-llms-rungpt

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 command injection vulnerability exists in the RunGptLLM class of the llama_index library, version 0.9.47, used by the RunGpt framework from JinaAI to connect to Language Learning Models (LLMs). The vulnerability arises from the improper use of the eval function, allowing a malicious or compromised LLM hosting provider to execute arbitrary commands on the client's machine. This issue was fixed in version 0.10.13. The exploitation of this vulnerability could lead to a hosting provider gaining full control over client machines.

Affected Packages

2 total 2 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIllama-indexall versions0.10.13
🐍PyPIllama-index-llms-rungptall versions0.1.3

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 0.10.13 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2024-4181 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-2024-4181 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-2024-4181. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

A command injection vulnerability exists in the RunGptLLM class of the llama_index library, version 0.9.47, used by the RunGpt framework from JinaAI to connect to Language Learning Models (LLMs). The vulnerability arises from the improper use of the eval function, allowing a malicious or compromised LLM hosting provider to execute arbitrary commands on the client's machine. This issue was fixed in version 0.10.13. The exploitation of this vulnerability could lead to a hosting provider gaining full control over client machines.
O3 Security · Impact-Aware SCA

Is CVE-2024-4181 in your dependencies?

O3 detects CVE-2024-4181 across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.