Shell Injection Vulnerability in Langflow Tool by Langflow AI
CVE-2026-33475

9.1CRITICAL

Key Information:

Vendor

Langflow-ai

Status
Langflow
Vendor
CVE Published:
24 March 2026

What is CVE-2026-33475?

Langflow, a tool designed for building AI-powered agents, is vulnerable to a shell injection issue affecting its GitHub Actions workflows. This vulnerability permits unauthenticated attackers to execute arbitrary commands by exploiting the unsanitized interpolation of user-controlled GitHub context variables in shell commands. Attackers can leverage this flaw to exfiltrate secrets like the GITHUB_TOKEN, potentially leading to severe supply chain compromises and unauthorized manipulation of CI/CD processes. Upgrading to version 1.9.0 patches the vulnerability and protects against these attack vectors.

Affected Version(s)

langflow < 1.9.0

References

https://github.com/langflow-ai/langflow/security/advisori...
x_refsource_CONFIRM

CVSS V3.1

Score:
9.1
Severity:
CRITICAL
Confidentiality:
High
Integrity:
High
Availability:
High
Attack Vector:
Network
Attack Complexity:
Low
Privileges Required:
None
User Interaction:
None
Scope:
Unchanged

Timeline

  • Vulnerability published

  • Vulnerability Reserved

.