cve.nowby Sazabi
← All vulnerabilities
CVE-2026-109440EUVD-2026-104680GHSA-FCMR-J7XJ-36VP

LangAlpha through 2026.09.07 Indirect Prompt Injection RCE via Bash and ExecuteCode

Published
Last modified
Status
published
Known exploitation
Not listed in CISA KEV
Public exploit
None on Exploit-DB

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 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 versions

  • ginlix-ai LangAlpha

    through 2026.09.07

References 3

lasso.security

GitHub · ginlix-ai/LangAlpha

vulncheck.com