Skip to content
IBMCVE-2026-9196

IBM Langflow OSS: code injection

High8.1CVE-2026-9196 · Published Aug 5, 2026 · updated Aug 7, 2026

IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute unintended code during Agentic Assistant validation due to improper handling of LLM‑generated components. The application executes model‑generated Python code in the backend during validation prior to user approval, which may allow an attacker to trigger side effects such as outbound network access, file system interaction, or data exfiltration with the privileges of the Langflow backend process.

IBM advisory

Affected versions

PackageAffectedFixed in
Langflow OSS
Product
>= 1.0.0, <= 1.10.3No fix yet
Details and references
CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
Severity from
the vendor (its own CVE record or advisory)
Weakness
CWE-94

More IBM advisories

All IBM
Advisory
IBM Langflow OSS: weak cryptography
High7.4Aug 5
IBM Langflow OSS: code execution
High8.8Aug 5
IBM Langflow OSS: information disclosure
High7.1Aug 5
IBM Langflow OSS: code injection
High8.8Aug 5
IBM Langflow OSS: broken cryptography
High7.4Aug 5
IBM Langflow OSS: path traversal
Medium6.5Aug 5

Critical advisories by email

Wednesdays: the week’s critical and high advisories in the AI and data stack, with the fixed versions. Only in weeks that have some.

Double opt-in. Unsubscribe any time.