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.

Metrics

Attack Vector Network

Attack Complexity Low

Privileges Required None

Attack Requirements None

User Interaction Passive

Vulnerable System Confidentiality Impact High

Vulnerable System Integrity Impact High

Vulnerable System Availability Impact High

Subsequent System Confidentiality Impact None

Subsequent System Integrity Impact None

Subsequent System Availability Impact None

Attack Vector Network

Attack Complexity Low

Privileges Required None

Scope Unchanged

Confidentiality Impact High

Integrity Impact High

Availability Impact High

User Interaction Required

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

Exploitation poc

Automatable no

Technical Impact total

Affected Vendors & Products

Vendors Products
Ginlix-ai
  • Langalpha

No data.

No data.

References
Link Providers
https://github.com/ginlix-ai/LangAlpha/blob/435a5a44fabdeb33e409a62d233a936d96241c86/src/ptc_agent/agent/agent.py#L524 cve-icon cve-icon
https://www.lasso.security/vulnerability-database/cve-2026-109440 cve-icon cve-icon
https://www.vulncheck.com/advisories/langalpha-through-2026.09.07-indirect-prompt-injection-rce-via-bash-and-executecode cve-icon cve-icon
History

Fri, 23 Oct 2026 00:45:00 +0000

Type Values Removed Values Added
Metrics cvssV3_1

{'score': 8.1, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:N'}

cvssV4_0

{'score': 8.6, 'vector': 'CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N'}

 ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'total'}, 'version': '2.0.3'}

cvssV3_1

{'score': 8.8, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H'}

cvssV4_0

{'score': 8.7, 'vector': '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'}

Wed, 21 Oct 2026 17:15:00 +0000

Type Values Removed Values Added
First Time appeared Ginlix-ai
Ginlix-ai langalpha
Vendors & Products Ginlix-ai
Ginlix-ai langalpha

Tue, 20 Oct 2026 01:15:00 +0000

Type Values Removed Values Added
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.
Title LangAlpha through 2026.09.07 Indirect Prompt Injection RCE via Bash and ExecuteCode
Weaknesses CWE-1427
References
Metrics cvssV3_1

{'score': 8.1, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:N'}

cvssV4_0

{'score': 8.6, 'vector': 'CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N'}
cve-icon MITRE

Status: PUBLISHED

Assigner: VulnCheck

Published: 2026-10-20T00:46:05.334Z

Updated: 2026-10-22T21:16:20.124Z

Reserved: 2026-10-12T15:52:36.683Z

Link: CVE-2026-109440

cve-icon Vulnrichment

Updated: 2026-10-22T21:16:16.426Z

cve-icon NVD

Status : Deferred

Published: 2026-10-20T01:17:10.103

Modified: 2026-10-22T22:18:00.100

Link: CVE-2026-109440

cve-icon Redhat

No data.