LangAlpha indirect prompt injection allows remote code execution

LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability allowing remote attackers to execute shell commands and Python code by planting instructions in web content retrieved by the agent, potentially exfiltrating vault secrets.

Disclosed 20 October 2026 · Record updated 20 October 2026

Impact

Remote attackers can execute arbitrary code in the workspace sandbox and exfiltrate vault secrets from internal configuration files due to lack of allow-list and human-in-the-loop approval mechanisms.

Our coverage

A marionette puppet dangles from invisible strings attached to a malicious webpage, its wooden arms jerking to execute commands at a workbench without hesitation.

Vulnerabilities

Web pages can hijack LangAlpha agent and run shell commands

A CVE published on 20 October 2026 says the ginlix-ai coding agent executes attacker instructions found in retrieved web content, with no approval step.

20 Oct 2026

Sources

nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-109440