---
id: CVE-2026-109440
title: >-
  LangAlpha through 2026.09.07 Indirect Prompt Injection RCE via Bash and
  ExecuteCode
summary: >-
  LangAlpha through 2026.09.07 contains an indirect prompt injection
  vulnerability that allows remote attackers to execute shell commands or Python
  by planting instructions in web content retrieved by the agent. Because Bash
  and ExecuteCod…
severity: high
cvss: 8.1
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:N'
cvssSource: cna
cwe:
  - CWE-1427
vendor: ginlix-ai
product: LangAlpha
affected:
  - LangAlpha <= 2026.09.07
published: '2026-10-20'
updated: '2026-10-20'
sourceUpdated: '2026-10-20T00:46:05.334Z'
source: CVEORG
sourceUrl: 'https://www.cve.org/CVERecord?id=CVE-2026-109440'
references:
  - url: 'https://www.lasso.security/vulnerability-database/cve-2026-109440'
    label: Lasso.security Advisory
  - url: >-
      https://github.com/ginlix-ai/LangAlpha/blob/435a5a44fabdeb33e409a62d233a936d96241c86/src/ptc_agent/agent/agent.py#L524
  - url: >-
      https://www.vulncheck.com/advisories/langalpha-through-2026.09.07-indirect-prompt-injection-rce-via-bash-and-executecode
    label: >-
      VulnCheck Advisory: LangAlpha through 2026.09.07 Indirect Prompt Injection
      RCE via Bash and ExecuteCode
tags:
  - cve.org
ingestedAt: '2026-10-20T01:49:42.628Z'
---

## Overview

LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability that allows remote attackers to execute shell commands or Python by planting instructions in web content retrieved by the agent. Because Bash and ExecuteCode lack an allow-list and human-in-the-loop approval, attackers can run code in the workspace sandbox and exfiltrate vault secrets from _internal/.vault_secrets.json.

## Affected

- `LangAlpha <= 2026.09.07`

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.