CVE-2026-109440
CVE-2026-109440
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.
Published .
CVSS v3 metric
CVSS v3 base score 8.1 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:N.
EPSS exploit prediction
No EPSS score from FIRST.org yet. New CVEs usually get one within a few days; no score means no signal yet, not low risk. How EPSS works.
Weakness classification (CWE)
References
- github.com/ginlix-ai/LangAlpha/blob/435a5a44fabdeb33e409a62d233a936d96241c86/sr… (technical-description)
- www.lasso.security/vulnerability-database/cve-2026-109440 (technical-description, exploit)
- www.vulncheck.com/advisories/langalpha-through-2026.09.07-indirect-prompt-injec… (third-party-advisory)
Frequently asked questions
- What is CVE-2026-109440?
- CVE-2026-109440 is a high-severity vulnerability, classified under CWE-1427. CVSS score: 8.1/10. Published 2026-10-20.
- How severe is CVE-2026-109440?
- High severity. CVSS v3 base score is 8.1 out of 10.