AI Sec Watch: A Security Intelligence Platform for AI Systems

Luu, T.J.

CriticalVulnerability

GHSA-2xxc-73fv-36f7: llama-index vulnerable to arbitrary code execution

Source: GitHub Advisory(opens in a new tab)
Identifiers: CVE-2023-39662GHSA-2xxc-73fv-36f7
Published: August 15, 2023
Record updated: October 10, 2026

View JSON

Affected: llama-index < 0.9.14
Fixed in: 0.9.14
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 1.5%

Summary

An issue in llama_index v0.7.13 and earlier lets a remote attacker execute arbitrary code through the `exec` parameter in the PandasQueryEngine function. The source describes the flaw and its impact but gives no further detail on exploitation conditions.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 9.8(critical)
Patch available: Yes
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector: network
Attack complexity: low
Privileges required: none
User interaction: none
EPSS: 1.5%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on October 10, 2026.
Disclosure date: August 15, 2023

Weaknesses and techniques

Weakness (CWE): CWE-74
CWE-94
Attack pattern (CAPEC): CAPEC-242

Affected

Packages: llama-index@< 0.9.14 (fixed: 0.9.14)
Vendors: LangChain

Classification

Attack type: Other
Attack sophistication: Trivial
AI component targeted: Framework
Impact: Confidentiality,
Integrity,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative.

Original source: https://github.com/advisories/GHSA-2xxc-73fv-36f7

First tracked: October 10, 2026 at 12:53 AM ET, from GitHub Advisory Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

llama-indexPyPILLM dependency since 2023-02-16 · 12 tracked dependents

Summary

Mitigation

Affected packages in the Exposure Registry

Related items