AI Threat AlertAI Security Threat Feed
Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 533 results — Critical severityCVE-2025-45150ChatGLM-Webui: arbitrary file read, no auth required9.80.6%langchain-chatglm-webuiAug 1CRITECVE-2025-54381BentoML: unauthenticated SSRF via file upload URLs9.913.2%bentomlJul 29CRITECVE-2025-46059LangChain GmailToolkit: indirect prompt injection to RCE9.80.8%—Jul 29CRITECVE-2025-5120smolagents: sandbox escape enables unauthenticated RCE10.031.2%smolagentsJul 27CRITECVE-2025-6853Langchain-Chatchat: path traversal in KB upload9.80.6%langchain-chatchatJun 29CRITECVE-2025-53002LLaMA-Factory: RCE via unsafe checkpoint deserialization9.81.3%llamafactoryJun 26CRITECVE-2025-2828LangChain RequestsToolkit: SSRF exposes cloud metadata10.021.0%langchainJun 23CRITECVE-2025-1793llama_index: SQL injection in vector store integrations9.80.7%llama-indexJun 5CRITECVE-2025-1750LlamaIndex DuckDB: SQL injection enables file R/W and RCE9.80.9%llama-indexJun 2CRITECVE-2025-47277vLLM: RCE via exposed TCPStore in distributed inference9.81.0%vllmMay 20CRITECVE-2025-47241browser-use: URL allowlist bypass enables SSRF in agents9.30.5%browser-useMay 5CRITECVE-2025-32444vLLM: RCE via pickle deserialization on ZeroMQ9.81.8%vllmApr 30CRITECVE-2025-45949PHPGurukul: session hijack via password change flow9.80.5%—Apr 28CRITECVE-2025-45953PHPGurukul Hostel Mgmt: session hijacking → takeover9.10.4%—Apr 28CRITGHSA-ggpf-24jw-3fcwvLLM: RCE via malicious model, PyTorch < 2.6 bypass9.8—vllmApr 23CRITECVE-2025-32434PyTorch: RCE bypasses weights_only=True safe-load guard9.82.4%pytorchApr 18CRITECVE-2025-32428jupyter-remote-desktop-proxy: VNC network exposure—0.9%jupyter-remote-desktop-proxyApr 12CRITECVE-2025-32375BentoML: RCE via insecure deserialization in runner9.852.4%bentomlApr 9CRITCVE-2025-3248Langflow: Unauth RCE via code injection endpoint9.8100.0%langflowApr 7CRITECVE-2025-27520BentoML: unauthenticated RCE via insecure deserialization9.840.6%bentomlApr 4Frequently asked questions
What is an AI security threat feed?
An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.
Which sources are the AI CVEs tracked from?
CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.
What AI systems do these vulnerabilities affect?
Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.
How often is the AI threat feed updated?
The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.
Is the AI security feed free?
Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.
Need deeper analysis?
Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.
Start 14-Day Free Trial