← CVE Radar
CVE-2026-109440LangAlpha through 2026.09.07 Indirect Prompt Injection RCE via Bash and ExecuteCode
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.
8.7 HIGHEPSS 0.60%Not in KEVNVD: Deferred
Overview
Severity
| Score | Severity | Version | Vector String |
|---|---|---|---|
| 8.7 | HIGH | 4.0VulnCheck (CNA) | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N |
| 8.8 | HIGH | 3.1VulnCheck (CNA) | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
Details
- CVE ID
- CVE-2026-109440
- Status
- Deferred
- Assigner (CNA)
- VulnCheck
- Published
- Oct 20, 2026
- Last modified
- 2026-10-22 22:18 UTC
- Weaknesses
- CWE-1427 · Improper Neutralization of Input Used for LLM Prompting
Affected Products
As published by the CNA in the CVE record.
ginlix-aiLangAlpha1 version range
- through 2026.09.07
References
- github.com https://github.com/ginlix-ai/LangAlpha/blob/435a5a44fabdeb33e409a62d233a936d96241c86/src/ptc_agent/agent/agent.py#L524
- lasso.security https://www.lasso.security/vulnerability-database/cve-2026-109440
- vulncheck.com https://www.vulncheck.com/advisories/langalpha-through-2026.09.07-indirect-prompt-injection-rce-via-bash-and-executecode