CVE-2026-109440
CVE-2026-109440 · LangAlpha through 2026.09.07 Indirect Prompt Injection RCE via Bash and ExecuteCode
This page contains facts from public vulnerability sources. Check the original advisory before updating.
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.
CVSS 8.7 · High · EPSS 0.5%
- Published
- Updated
Affected products and versions
langalpha
- Versions
- ≥ 0, ≤ 2026.09.07: Affected (custom)
No fix published
Original sources
- https://www.lasso.security/vulnerability-database/cve-2026-109440
- https://github.com/ginlix-ai/LangAlpha/blob/435a5a44fabdeb33e409a62d233a936d96241c86/src/ptc_agent/agent/agent.py#L524
- https://www.vulncheck.com/advisories/langalpha-through-2026.09.07-indirect-prompt-injection-rce-via-bash-and-executecode
- https://nvd.nist.gov/vuln/detail/CVE-2026-109440