Articles
Daily digests summarizing the vulnerabilities and incidents tracked by VulnWatch.
-
· 89 entries · weekly
VulnWatch Weekly: The Agentic Apocalypse & The Langflow Meltdown
This week marks a turning point for AI security as critical RCEs plague agentic frameworks like Mistral Vibe and Langflow. With 89 new entries, the dominant theme is the collapse of trust boundaries in autonomous agents and model serving pipelines.
-
· 17 entries · daily · Subscribers only
VulnWatch Daily: Critical GitPython RCE, DeepSeek Auth Bypass, and vLLM Data Leaks
Today's digest highlights a critical config corruption flaw in GitPython enabling RCE, an authentication bypass in DeepSeek Harness, and cross-user data leakage in vLLM inference kernels.
-
· 4 entries · daily · Subscribers only
VulnWatch Digest: RPC Assertions, GGUF Overflows, and Supply Chain Risks
Today's briefing covers critical integrity flaws in llama.cpp RPC servers, integer overflows in Ollama's GGUF decoder, and supply chain prompt injection risks in Elixir tooling.
-
· 98 entries · weekly
VulnWatch Weekly: The Week of Unsafe Eval, Agent RCE, and Active SSRF
This week's digest highlights a critical wave of Remote Code Execution (RCE) vulnerabilities in LLM inference servers, driven by unsafe deserialization and dynamic code evaluation. Most urgently, CISA has added an actively exploited MLflow SSRF flaw to its KEV catalog, demanding immediate patching for all exposed instances.
-
· 25 entries · daily · Subscribers only
VulnWatch Daily: Critical Agent Supply-Chain Poisoning and CodeWhale RCE
Today's digest highlights critical vulnerabilities in agentic workflows, including Kraken cache poisoning and CodeWhale auto-execution flaws. NVIDIA Triton and MONAI also require immediate attention for DoS and RCE risks.
-
· 68 entries · weekly
VulnWatch Weekly: Critical RCE in MindsDB & Agentic Supply Chain Risks
This week's digest highlights a CVSS 10.0 RCE in MindsDB allowing unauthenticated command execution via LLM prompts. We also analyze critical prototype pollution in Trigger.dev, template injection in Prompty, and widespread SSRF/RCE risks in the emerging Model Context Protocol (MCP) ecosystem.
-
· 6 entries · daily · Subscribers only
VulnWatch Daily: Critical File Reads in Firecrawl & Agent RCE in Goose
Today's digest covers critical vulnerabilities in AI data pipelines and agentic frameworks, including arbitrary file reads in Firecrawl, unauthorized file access in Flowise, and pre-prompt RCE in the Goose agent.
-
· 33 entries · daily · Subscribers only
Langflow Catastrophe: 15 Critical Flaws Enable Unauthenticated RCE
A massive cluster of critical vulnerabilities in IBM Langflow allows unauthenticated remote code execution via default configurations. Additional risks identified in AI IDEs, MCP servers, and inference engines require immediate attention.
-
· 60 entries · daily · Subscribers only
VulnWatch Daily: Critical Auth Bypasses in Langflow & Cognee; vLLM RCE Surge
Today's digest highlights critical authentication failures in Langflow and Cognee, alongside a significant cluster of RCE and DoS vulnerabilities in vLLM and MLflow affecting model serving and pipeline integrity.
-
· 79 entries · weekly
VulnWatch Weekly: Langflow Cascade & MCP Ecosystem Risks
Langflow faces a critical week with 10+ CVEs including RCE and secret leakage. MCP servers show systemic auth flaws. Action required on model loading.
-
· 4 entries · daily · Subscribers only
VulnWatch Daily: Critical Pickle Scanning Flaws and ONNX Runtime Risks
Today's digest highlights critical bypasses in model safety scanning and pickle detection, alongside runtime stability issues in ONNX and agentic memory handlers. Immediate patching is advised for serialization tools.
-
· 10 entries · daily · Subscribers only
VulnWatch Daily: MCP Servers Face Injection Risks; Triton DoS Patched
Today's digest highlights critical injection flaws in Model Context Protocol servers, alongside denial-of-service vectors in NVIDIA Triton and supply-chain risks in AI development tools.
-
· 120 entries · weekly
VulnWatch Weekly: Agentic RCE & Supply Chain Risks Surge
Critical vulnerabilities in Langflow, vLLM, and MCP servers highlight severe risks in AI tooling. Immediate patching required for agentic platforms and inference engines to prevent RCE and supply chain compromise.
-
· 23 entries · daily · Subscribers only
VulnWatch Daily: Critical MCP Agent Flaws and Supply Chain Compromises
23 new vulnerabilities reported today including CVSS 10.0 MCP server flaws, compromised litellm wheels, and critical Incus RCEs. Immediate patching recommended for agent frameworks and container infrastructure.
-
· 21 entries · daily · Subscribers only
VulnWatch Daily: Critical Agentic RCE in ToolJet, Flowise, and Cursor
Today's digest highlights critical RCE vulnerabilities in AI agent platforms including ToolJet and Flowise, alongside supply chain risks in model loading and authentication bypasses in LibreChat.