CVE-2026-33873: Langflow arbitrary Python execution through Agentic Assistant validation

Summary

Langflow versions prior to 1.9.0 contain CVE-2026-33873 in the Agentic Assistant feature. Its validation phase executes LLM-generated Python code, reaching dynamic execution sinks and instantiating the generated class server-side. Where an attacker can access the feature and influence model output, this allows arbitrary server-side Python execution.

Mitigation

Version 1.9.0 fixes the issue.

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

• langflowPyPIReaches an LLM package through dependencies

Topics

• AI agents

Related items

• HighCVE-2026-123818: LMDeploy is a toolkit for compressing, deploying, and serving large language models. From 0.12.3 until 0.15.0…Similar attack · NVD/CVE Database
• HighGHSA-vvr2-h2jp-838m: Code Graph RAG: MCP paginated read_file path traversal / arbitrary file readSimilar attack · GitHub Advisory Database
• MediumAttackers Crash Claude's 'Office Party' Flaw to Run Malicious Code on LinuxSimilar attack · Dark Reading
• MediumCVE-2026-124588: huggingface finetrainers code injection via Library argumentSimilar attack · NVD/CVE Database
• MediumTaiwan-Based Hacker Used BOSSAI AI Agents to Steal Taipei Emergency Dispatch RecordsSimilar attack · The Hacker News