Langflow
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 4
- European cyber threats accelerate as AI infrastructure draws attacks
TechRadar reports that Proofpoint telemetry detected 4.5 times as many phishing emails in Europe compared with 2025, versus 1.5 times in other regions, while phishing detections per million inbound messages rose 3.2 times. Proofpoint also observed more than 188,000 AI-enabled applications connected through authentication and OAuth frameworks, and reported targeting of open-source AI projects including Langflow and LiteLLM.
TechRadar · 🔥 0 - Langflow 1.13.0 patches critical auth bypass and RCE flaws
Langflow 1.13.0 addresses vulnerabilities affecting Langflow OSS 1.0.0 through 1.12.8, including CVE-2026-93680 and CVE-2026-110186, both rated CVSS 9.8 by IBM. According to iThome 台湾, the former may allow remote authentication bypass, while the latter may enable unauthenticated remote code execution through improper code-generation controls; IBM also identified a potential RCE path involving MCP tool enumeration. The release disables automatic login by default in official packages, while other reported issues involve Agentic Assistant, API credential protection, and vulnerabilities in the bundled Hono framework.
iThome 台湾 · 🔥 0 - A hands-on tour of popular AI open-source tools
This Juejin tutorial organizes AI open-source tools around three common needs: local model chat, agent orchestration, and multimodal understanding. It demonstrates Ollama with Qwen3 4B, including installation, model download, local chat, and API access, before showing a vLLM server for Qwen2-VL-2B-Instruct. The article also recommends consulting each project’s official GitHub repository and README, and suggests lightweight models when VRAM is limited.
掘金 · 人工智能 · 🔥 0 - Langflow RCE flaw CVE-2026-105740 draws 3,460 exploit attempts
iThome reports that a critical vulnerability in the open-source low-code AI development platform Langflow, tracked as CVE-2026-105740, has a severity score of 9.9 and has been targeted by more than 3,400 observed exploit attempts. The flaw lets authenticated attackers inject arbitrary system commands, including remote code execution, through MCP (Model Context Protocol) Stdio transport, and affects versions before 1.9.0; the maintainers published the advisory on the 5th of the month and released Langflow 1.9.0. Attack data comes from the security firm Previdian, which said it first saw attempted exploitation on September 19 and saw activity rise notably from October 11; by October 15 its honeypots had logged 1,423 attempts, and by the morning of October 22 the count reached 3,460 from 31 IP addresses across 17 countries and regions including Taiwan, China, Hong Kong, Japan, South Korea, Singapore, the US and Germany. Previdian said the CVE had not been added to CISA's Known Exploited Vulnerabilities catalog at the time of reporting.
iThome 台湾 · 🔥 0
Experience and discussion from the community
Share my Langflow experienceAsk about Langflow
Nobody has shared their experience with Langflow yet.