CVE-2026-109440 LangAlpha through 2026.09.07 Indirect Prompt Injection RCE via Bash and ExecuteCode
HighCVSS 8.7
EPSS 0.60%
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- Proof of concept public · automatable: no · technical impact: total
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.
Upgrade path
1 package: 1 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| ginlix-ai/langalpha | <= 2026.09.07 | after 2026.09.07 | Fixed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| ginlix-ai/langalpha | <= 2026.09.07 | No fix listed |
References
- Lasso.security Advisory exploit technical-description
- github.com technical-description
- VulnCheck Advisory: LangAlpha through 2026.09.07 Indirect Prompt Injection RCE via Bash and ExecuteCode third-party-advisory
- ENISA EUVD EUVD-2026-104680 third-party-advisory