Authenticated Python execution via LLM-generated validation code
Published Mar 27, 2026 · Updated Mar 27, 2026
Code injection in Langflow OSS before 1.9.0 allows remote authenticated users to execute arbitrary Python through Agentic Assistant. The validation path extracts LLM-generated component code, passes it to create_class(), executes compiled definitions and class code with exec(), and instantiates the resulting class. Access to Agentic Assistant and influence over model output are required; execution runs in the server process and permits file access, command execution, and secret disclosure.
Summary
What happened
Code injection in Langflow OSS before 1.9.0 allows remote authenticated users to execute arbitrary Python through Agentic Assistant. The validation path extracts LLM-generated component code, passes it to create_class(), executes compiled definitions and class code with exec(), and instantiates the resulting class. Access to Agentic Assistant and influence over model output are required; execution runs in the server process and permits file access, command execution, and secret disclosure.
The record
- CVE
- CVE-2026-33873
- Published
- Mar 27, 2026
- Updated
- Mar 27, 2026
- Vendor
- OpenBMC Project
- Product
- Langflow OSS
- Classifications
- CWE-94, T1059.006, T1190
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Mar 27, 2026CVE publishedPublication date reported by the CVE source.
- Mar 27, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 1.9.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Upstream Agentic Assistant validation proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo