Articles
Daily digests summarizing the vulnerabilities and incidents tracked by VulnWatch.
-
· 8 entries · daily · Subscribers only
VulnWatch Daily: Critical LiteLLM Auth Bypass and RAG Injection Risks
Today's digest highlights a critical authentication bypass in LiteLLM allowing admin takeover, multi-tenant isolation failures in Amazon Strands, and new injection vectors in GraphRAG and terminal integrations.
-
· 26 entries · daily · Subscribers only
VulnWatch Daily: Critical RCE in vLLM and Agentic Frameworks Compromised
Today's digest highlights a critical remote code execution flaw in vLLM allowing arbitrary Python execution via model revisions, alongside severe prompt injection and path traversal vulnerabilities in agentic frameworks like CrewAI and HKUDS Vibe-Trading.
-
· 31 entries · daily · Subscribers only
VulnWatch Digest: Critical RCE in Agentic Frameworks and A2A Protocol Flaws
Today's digest highlights critical remote code execution vulnerabilities in Langchain-Chatchat and piflow, alongside a wave of authentication and data leakage issues in the emerging Agent2Agent (A2A) protocol stack.
-
· 21 entries · daily · Subscribers only
VulnWatch Daily: Critical RCE in Agentic Meshes and SGLang DoS Surge
Today's digest highlights a critical authentication bypass in Google's OSS Agent Mesh allowing arbitrary tool invocation, alongside a wave of denial-of-service vulnerabilities in SGLang's disaggregation backend. Supply chain risks in Apache Camel and BentoML also demand immediate attention.
-
· 80 entries · weekly
VulnWatch Weekly: Agentic RCE, MCP Supply Chain, and Model DoS Surge
This week saw a critical surge in agentic vulnerabilities, with CVE-2026-96620 enabling RCE in Claude Agent SDK and deep flaws in MCP servers. Model serving stacks like SGLang and vLLM faced severe DoS vectors, while supply-chain risks in Podman and DeepSeek demand immediate patching.
-
· 1 entry · daily · Subscribers only
VulnWatch Daily: Heap OOB in cgltf Risks AI 3D Pipelines
A medium-severity heap out-of-bounds read in cgltf (CVE-2026-112019) allows crafted glTF files to leak memory or crash applications, posing risks to AI systems processing 3D assets for simulation and generative modeling.
-
· 16 entries · daily · Subscribers only
VulnWatch Daily: Critical RCE in LMCache, Agentic Injection in Claude SDK, and Supply Chain Risks
Today's digest highlights critical remote code execution flaws in LMCache and SGLang, a dangerous argument injection in the Claude Agent SDK, and severe supply chain vulnerabilities in DeepSeek and MariaDB affecting AI infrastructure.
-
· 20 entries · daily · Subscribers only
VulnWatch Daily: Critical Agentic RCEs and Supply Chain Failures
Today's digest highlights critical vulnerabilities in AI agent frameworks, including Nginx UI directive injection and KEDA privilege escalation. We also cover severe supply chain risks in Podman and Claude Code, alongside multiple DoS vectors in vLLM and SGLang.
-
· 11 entries · daily · Subscribers only
VulnWatch Digest: Critical MCP DoS, NullHub Auth Bypass, and Supply Chain Risks
Today's digest highlights critical authentication failures in NullHub, unbounded memory consumption in Model Context Protocol SDKs, and supply chain risks in Ludwig and GUIX. Immediate patching is recommended for agentic infrastructure.
-
· 9 entries · daily · Subscribers only
VulnWatch Daily: Agentic Sandbox Escapes and SSRF in Model Servers
Today's digest highlights critical sandbox escapes in Heym and GitLab agents, widespread SSRF flaws in Mistral.rs and Conductor, and ACL bypasses in Model Context Protocol servers.
-
· 23 entries · daily · Subscribers only
VulnWatch Daily: Critical MCP Flaws and SGLang DoS Waves
Today's digest highlights critical authorization bypasses in Model Context Protocol servers, a cascade of denial-of-service vectors in SGLang, and severe prompt-injection risks in agentic frameworks.
-
· 120 entries · weekly
VulnWatch Weekly: The Week of Mass RCE in AI Agents and Orchestration
This week saw an unprecedented wave of Critical RCEs in AI orchestration tools like Langflow and PraisonAI, driven by unsandboxed code execution and prompt injection. Immediate patching is required for agent platforms, MCP servers, and model inference engines to prevent total host compromise.
-
· 14 entries · daily · Subscribers only
VulnWatch Daily: Critical Auth Flaws in LLM Gateways and Agent Sandboxes
Today's digest highlights critical authentication gaps in Katanemo Plano and LlamaFarm, alongside sandbox escape risks in mistral.rs. Immediate patching is required for exposed admin interfaces and symlink vulnerabilities affecting agentic workflows.
-
· 15 entries · daily · Subscribers only
VulnWatch Daily: Critical MCP Auth Flaws and Agent Sandbox Escapes
Today's digest highlights severe authorization gaps in Model Context Protocol (MCP) servers, configuration injection risks in LLM agents, and sandbox escapes in automated coding tools. Immediate patching is recommended for JeecgBoot, 9router, and mini-swe-agent deployments.
-
· 8 entries · daily · Subscribers only
VulnWatch Daily: Critical Agentic RCEs and MCP Server Exposures
Today's digest highlights critical RCE vulnerabilities in Astron Agent and unauthenticated access in x64dbg-MCP servers, alongside severe auth-bypass flaws in Nginx-UI and Vikunja affecting AI-adjacent platforms.