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 1961 results — Active exploitationCVE-2026-34225open-webui: blind SSRF via image-edit URL fetch4.30.3%open-webuiJul 7HIGHECVE-2026-26193Open WebUI: stored XSS via chat 'embeds' iframe escape7.30.2%open-webuiJul 7HIGHECVE-2026-26192Open WebUI: stored XSS via citation iFrame → admin RCE7.30.2%open-webuiJul 7HIGHECVE-2025-46719Open WebUI: chat XSS steals tokens, admin RCE—0.6%open-webuiJul 7MEDIECVE-2025-46571Open WebUI: Stored XSS via HTML upload enables admin RCE—0.4%open-webuiJul 7MEDIECVE-2026-44512onnx: crafted model triggers SIGSEGV in version_converter5.50.2%onnxJul 7UNKNECVE-2026-55615Langroid: unvalidated LLM Cypher enables graph RCE—0.5%langroidJul 6HIGHECVE-2026-54234vLLM: crafted spec-decoding request crashes GPU worker (DoS)7.50.6%vllmJul 6MEDIECVE-2026-55438Coder: CORS bypass via workspace subdomain proxy5.80.2%github.com/coder/coder/v2Jul 6HIGHECVE-2026-54771Langroid: auth bypass invokes disabled tools via raw JSON8.10.4%langroidJul 6CRITECVE-2026-54769Langroid: prompt injection to RCE via broken eval() sandbox10.00.9%langroidJul 6UNKNECVE-2026-54760Langroid: SQLChatAgent regex bypass exposes pg_read_file—0.6%langroidJul 6MEDIECVE-2026-55646vLLM: audio upload OOMs process before size check6.50.5%vllmJul 6LOWECVE-2026-14742LangGraph: weak hash in task cache risks poisoning3.10.2%langgraphJul 5LOWECVE-2026-14738exo: weak hash algorithm in vision feature cache key3.70.3%—Jul 5MEDIECVE-2026-14647ONNX: OOB read in shape inference parsing untrusted models4.30.4%onnxJul 4CRITECVE-2026-14535fickling: shared-state bug disables ML pickle allowlist check9.80.6%ficklingJul 4HIGHECVE-2026-14534fickling: denylist gaps let malicious pickles execute8.80.6%ficklingJul 4LOWECVE-2026-14630AI-fundermentals: weak hash exposes chat session data3.10.2%—Jul 4HIGHECVE-2026-12196HestiaCP: cronjob flaw lets low-priv users get root—0.4%—Jul 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