⚠️ CRITICAL vuln in langflow-ai langflow < 1.9.0 (CVE-2026-33873): Agentic Assistant allows remote code injection via LLM-generated Python. Patch to 1.9.0+ or restrict feature access immediately. Details: https://radar.offseq.com/threat/cve-2026-33873-cwe-94-improper-control-of-generati-cafbe4ee #OffSeq #CVE202633873 #AIsecurity