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 1908 results — High severityCVE-2026-116180vLLM: uninitialized tensor lets tenant crash engine7.70.3%vllmOct 25HIGHCVE-2026-116179vLLM: num_frames override enables memory-exhaustion DoS7.50.3%vllmOct 25HIGHCVE-2026-116178vLLM: multimodal metadata DoS crashes inference engine7.50.3%vllmOct 25HIGHCVE-2026-116177vLLM: decompression bomb in Nemotron-VL causes DoS7.50.3%vllmOct 25HIGHCVE-2026-116176vLLM: SSRF via X-Request-Id leaks NCCL KV-cache data8.20.3%vllmOct 25HIGHCVE-2026-116174vLLM: gRPC invalid token IDs crash EngineCore (DoS)7.50.3%vllmOct 25HIGHCVE-2026-116173vLLM: gRPC logprob limit bypass crashes EngineCore7.50.3%vllmOct 25HIGHCVE-2026-116172vLLM: gRPC top_n validation flaw crashes EngineCore7.50.3%vllmOct 25HIGHECVE-2026-113718virtualenv: GBK quote bypass in xonsh activation enables RCE—0.2%virtualenvOct 23HIGHECVE-2026-113723virtualenv: prompt injection enables shell command execution—0.2%virtualenvOct 23HIGHECVE-2026-112940filelock: SQLite symlink redirect enables file overwrite7.10.2%filelockOct 23HIGHCVE-2026-115419Strands Agents SDK: A2A session leak across callers8.10.4%—Oct 23HIGHCVE-2026-115586virtualenv: bash prompt injection allows command execution—0.3%virtualenvOct 23HIGHECVE-2026-73054SiYuan: WebSocket auth bypass leaks live event stream7.50.4%github.com/siyuan-note/siyuan/kernelOct 23HIGHECVE-2026-57845HF Datasets: pickle deserialization RCE via pandas builder8.80.5%datasetsOct 23HIGHECVE-2026-115477obsidian-tc: HITL approval bypass runs destructive tools—0.4%obsidian-tcOct 23HIGHECVE-2026-57146PraisonAI: unauthenticated A2U event streaming exposed7.50.5%praisonaiOct 23HIGHECVE-2026-57144PraisonAI: sandbox fails open, bypassing FS/network limits8.80.2%praisonaiOct 23HIGHECVE-2026-57142PraisonAI: recipe policy bypass self-approves shell tool7.80.2%praisonaiOct 23HIGHCVE-2026-57121PraisonAI: missing ownership check lets members delete data8.10.3%praisonaiOct 23Frequently 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