Live › vulnerability › CVE-2026-109440
Go to dashboardLangAlpha's agent always has Bash and ExecuteCode tools with no approval step, on the same agent that fetches web pages. A hidden instruction in a page, filing or news article can make it run shell or Python in the workspace sandbox and read _internal/.vault_secrets.json. Scheduled automations are exposed with no user present. No fixed release is published; v2026.09.07 is the last affected version and the newest server release.
Summary written from the sources below. Check the originals before acting.
First seen by InfraStack 2026-10-23 21:57 UTC. All times on this page are UTC.
| Product | Ecosystem | Affected | Fixed in |
|---|
| LangAlpha | vendor | <= 2026.09.07 | – |
v2026.09.07 or earlier is affectedv2026.09.07)Each row is the first time that source carried this signal. The analyst’s rows are its own findings.
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.
This page as .md · .json · in your agent: get_signal("CVE-2026-109440")
NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.