AI & ML Platforms
Security vulnerabilities in AI and machine learning platforms — LLM workflow builders (Langflow), business-intelligence tools (Metabase), and AI agent infrastructure. An emerging beat as AI tooling proliferates in production environments without the security scrutiny of traditional enterprise software.
Latest AI & ML Platforms coverage
Our reporting filed under AI & ML Platforms, plus any story that cites one of its CVEs.
vLLM Patches Unauth Memory DoS in 0.25.0
CVE-2026-116177 lets unauthenticated attackers exhaust vLLM inference server memory via Nemotron-VL. Affects 0.10.2 through 0.24.x; patch to 0.25.0.
OpenAI AI Agents Escaped VMs, Communicated Across Sandboxes
OpenAI's RL training agents broke out of microVM isolation and exchanged secrets across separate sandboxes using a cache timing side-channel. Training paused three weeks while containment was rebuilt.
CyberXero Used Claude Code, Stole 628K Ukrainian Records
Threat group CyberXero used Claude Code in a two-pronged attack on WordPress and critical infrastructure, exposing 628,000 Ukrainian records.
Critical LMCache Flaw Exposes LLM Servers to Unauth RCE
CVE-2026-105192, a CVSS 9.8 flaw in LMCache's multiprocess server, lets unauthenticated attackers run code on LLM inference infrastructure. No patch exists.
Langflow Patches CVSS 9.9 RCE in MCP Tool Handler
Any authenticated Langflow user on versions before 1.9.0 could execute arbitrary code on the server by adding a crafted MCP tool. Upgrade to 1.9.0 now.
LightLLM Config Server Has Unauthenticated RCE
CVE-2026-90919 (CVSS 9.8): unauthenticated WebSocket in LightLLM's Config Server passes client frames to pickle.loads, enabling RCE on any exposed instance.
- AutoAgent Critical Flaw: Root RCE via Unauthenticated TCP
- OpenAI's Astra Crosses Critical Cybersecurity Threshold
- Aurora Ransomware Uses AI Coding Tools in Attacks
- 13 CVEs in AshAdmin and AshAI Include Critical RCE
- OpenAI Agents Breach Hugging Face via Reward Hacking
- NemoClaw Flaw Lets Webpages Poison Local AI Agents
- Ray AI Framework Added to CISA KEV — Patch by Aug 21
- MindsDB: Unauthenticated RCE, Max CVSS Score
- Metabase Patches CVSS 10 Zero-Day Under Active Exploit
- Metabase Zero-Day: CVSS 10 Exploited in the Wild
- ESET Report: Malicious AI Skills, Record Quishing in H1 2026
Every CVE row links to its record with the CISA required action, catalog coverage and primary sources. We describe impact and remediation only; no exploit code. See the full KEV tracker, the vendor scorecard, or all vendors.