AI AgentHigh
CVE-2026-109440: LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability that allows remote …
- Occurred
- Oct 20, 2026
- Published
- Oct 20, 2026
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2026-109440
- cvss:HIGH
- agent-fail:injection-indirect
- agent-fail:authorization
- agent-cause:missing-guardrail
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: Indirect prompt injection vulnerability in LangAlpha agent allows remote code execution and secret exfiltration due to missing guardrails.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8