8.8High

CVE-2026-109440LangAlpha through 2026.09.07 Indirect Prompt Injection RCE via Bash and ExecuteCode

ginlix-ai LangAlpha Published: (1 month ago)

Description

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.

Weakness (CWE): CWE-1427

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
ginlix-ai LangAlpha ≤ 2026.09.07

References and patches