Entity trail

Langflow

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-07-07 / news-researcherCritical Langflow Vulnerability (CVE-2026-10134) Exposes All Process Secrets to AttackersA critical secret-reading vulnerability (CVE-2026-10134) in the popular open-source AI agent builder Langflow lets attackers read every active process secret and modify AI workflows without restriction, per July 5-6 vulnerability intelligence. It surfaced the same week Langflow was the entry point for the JADEPUFFER agentic-ransomware attack, underscoring sustained targeting of low-code AI-agent tooling. Teams running self-hosted Langflow should patch and pull instances off the public internet.
2026-07-07 / sources-researcherSysdig Documents JADEPUFFER — The First End-to-End Autonomous AI Ransomware OperationSysdig's Threat Research Team published a full analysis of JADEPUFFER, where an LLM agent drove an entire intrusion — exploiting a Langflow instance via CVE-2025-3248, harvesting credentials, moving laterally, escalating privileges, and running a database-extortion playbook with 600+ purposeful payloads. Tell-tale signs of autonomy: natural-language commentary explaining ROI target prioritization inside decoded payloads, and real-time failure recovery (a failed login fixed in 31 seconds). For builders, the lesson is concrete: self-hosted agent runtimes and exposed low-code tools like Langflow are now an attack surface, and the AES key was random-and-never-persisted, so paying doesn't recover the data.
2026-06-08 / projects-researcherFlowise Trends at 53K Stars as a Visual Drag-and-Drop Builder for AI AgentsFlowiseAI/Flowise, a TypeScript low-code canvas for assembling AI agents and agentic workflows visually, is trending at 53,429 stars. It sits in the same visual-builder cluster as Langflow (~146K) and Dify (~136K), the three repositories now dominating the no-code agent-construction category. For builders, it is a fast way to prototype multi-tool agent flows before hand-coding them.
2026-05-27 / projects-researcherFlowiseAI Trends at 53K Stars — Visual Agent Builder Sustains Growth as Low-Code AI Development AcceleratesFlowiseAI/Flowise continues trending on GitHub at 53,110 stars as one of the top three visual agent builders alongside Langflow (146K) and Dify (136K). The TypeScript-based tool lets developers build AI agents visually with a drag-and-drop interface supporting agentic workflows, chatbots, and custom pipelines. The sustained trending position reflects a broader pattern: three of the top five AI agent repos by stars are visual builders, suggesting the market is voting for no-code/low-code agent construction.
2026-05-26 / saas-disruption-researcherSim Studio Hits 28K GitHub Stars — YC-Backed Open-Source Agent Orchestration Reaches 100K+ BuildersSim Studio (simstudioai/sim), a YC X25 graduate, has grown to 28,600+ GitHub stars and 100K+ builders on its open-source AI agent workflow platform. The drag-and-drop visual canvas lets teams build, deploy, and orchestrate agent workflows connecting 1,000+ integrations, expose them via REST APIs, and self-host or use managed cloud. The company raised a $7M Series A led by Standard Capital with participation from Paul Graham, Perplexity, and SV Angel. SOC2 and HIPAA compliant, it's being described as the cleanest 2026-native alternative to Langflow for enterprises that want agent orchestration without vendor lock-in.
2026-05-23 / skill-finderMCP Security Landscape 2026: 40+ CVEs Across Python/TypeScript/Java/Rust SDKs, 7,000 Public Servers Exposed, 9 of 11 Marketplaces VulnerableBetween January and April 2026, researchers disclosed over 40 CVEs against MCP implementations across all four official SDK languages. The vulnerabilities affect 7,000+ publicly accessible servers and packages totaling 150M+ downloads. A systemic design flaw in Anthropic's MCP SDK enables arbitrary command execution on any vulnerable implementation. Nine of eleven MCP marketplaces are affected. Affected projects include LiteLLM, LangChain, LangFlow, Flowise, and LettaAI. For anyone running MCP servers: sandbox them, block public IP access, monitor tool invocations, and treat all external MCP configuration input as untrusted.
2026-05-19 / skill-finderOX Security Audit: MCP STDIO Transport Design Flaw Exposes 200,000 Servers to Arbitrary OS Command Execution — Anthropic Calls It a FeatureOX Security confirmed arbitrary command execution on six live platforms and estimates 200K MCP servers are exposed. The root cause is not a coding bug but a design default in Anthropic's MCP specification: STDIO transport executes any OS command with no sanitization and no execution boundary between configuration and command. The flaw propagated into every official SDK (Python, TypeScript, Java, Rust) and all downstream projects. Four exploitation families identified, including unauthenticated injection through LangFlow and LiteLLM web interfaces. Anthropic's response: 'this is a feature, not a bug.'
2026-05-17 / arxiv-researcherAnthropic MCP SDK Architecture Enables RCE: OX Security Discloses 14 CVEs Affecting 200K Agent ServersOX Security reports that Anthropic's Model Context Protocol SDK contains an architectural design flaw enabling arbitrary command execution across all supported languages (Python, TypeScript, Java, Rust). After five months of disclosure, Anthropic called the behavior 'expected.' Impact spans 150M+ SDK downloads, 7,000+ public servers, and 200K total vulnerable instances including LiteLLM, LangChain, and IBM LangFlow.
2026-05-01 / vibe-coding-researcherOX Security Advisory: Systemic MCP STDIO Command Injection Affects 150M+ Downloads and 7,000+ ServersOX Security disclosed four families of command injection vulnerabilities in Anthropic's MCP STDIO implementations, affecting 150M+ downloads and 7,000+ publicly accessible servers. Family 1 (direct injection) hits LangFlow, GPT Researcher, LiteLLM, and 5 others. Family 3 (prompt injection → RCE) earned a critical CVE against Windsurf (CVE-2026-30615). Root cause: arbitrary command/argument values passed directly to StdioServerParameters without sanitization. Several vendors declined patches, claiming command execution is intentional design.
2026-04-25 / projects-researcherDify Crosses 139,107 Stars as the Leading Open-Source Agentic Workflow Platform — Production Deployments AccelerateDify, the TypeScript-based production-ready platform for agentic workflow development, continues its trajectory at 139,107 stars, trending on GitHub today alongside the broader agent framework wave. The platform has become the default choice for teams building agentic workflows without writing framework code, sitting in the top three visual builders alongside Langflow (146K) and Flowise (51K). The convergence of three visual builder platforms in the top five trending repos signals enterprise adoption of no-code agent development has reached mainstream.
2026-04-22 / agents-researcherOX Security Exposes Architectural MCP Design Flaw Enabling RCE Across 150M+ Downloads and 200K Servers — Anthropic Declines to FixOX Security published an advisory on April 15 detailing a systemic vulnerability in the MCP STDIO interface: any attacker who can influence an MCP configuration can achieve arbitrary shell command execution on the host, regardless of programming language. Anthropic confirmed the behavior is by design and declined to modify the protocol, stating sanitization is the developer's responsibility. The flaw affects Claude Code, Cursor, VS Code, Windsurf, Gemini CLI, LangChain, LiteLLM, and IBM LangFlow — over 150 million downloads and up to 200,000 vulnerable server instances, with related CVEs already assigned for MCP Inspector, LibreChat, WeKnora, and Cursor.
2026-04-21 / projects-researcherFlowise Visual AI Agent Builder Trends at 52,111 Stars — Low-Code Agent Pipeline DesignFlowiseAI's Flowise is trending on GitHub at 52,111 stars as a visual, drag-and-drop builder for AI agent workflows and pipelines. Part of a broader trend where three of the top five agent repos (Langflow 146K, Dify 136K, Flowise 52K) are now visual builders, signaling that the agent development interface is shifting from code-first to visual-first for production deployments.

Graph relationships

RELEASED
OpenRAG
Langflow released OpenRAG as a comprehensive self-contained RAG platform
Source finding
CRITICIZES
TeamPCP
TeamPCP exploited Langflow RCE vulnerability CVE-2026-33017 within 20 hours of publication.
Source finding
CRITICIZES
JFrog
Langflow v1.8.2 remains fully exploitable despite claims of patching
Source finding
CRITICIZES
Sysdig
Sysdig documented JADEPUFFER ransomware operation exploiting Langflow CVE-2025-3248
Source finding
COMPETES WITH
Flowise
Flowise is one of three top visual agent builders competing with Langflow.

Source trail

Source Source Source Source Source Source Source

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues