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 2876 results — no patchCVE-2026-120194json-glib: infinite loop in JSONPath slice causes DoS7.5—rhoai/odh-mlflow-operator-rhel9Oct 31HIGHCVE-2026-16760fickling: safe-import trust bypass allows pickle RCE8.80.5%—Oct 30HIGHCVE-2026-118938fickling: dotted-name bypass lets malicious pickle pass scan8.80.5%ficklingOct 30CRITCVE-2026-62863MoLing: unauthenticated SSE enables browser-based tool calls9.60.3%—Oct 30MEDICVE-2026-59993picotls: HelloRetryRequest null deref crashes TLS clients6.50.2%picotlsOct 30HIGHCVE-2026-119337RAGFlow: missing authz lets users run others' agents7.10.3%—Oct 30HIGHCVE-2026-119978Flowise: sandbox escape allows authenticated RCE8.50.3%FlowiseOct 30MEDICVE-2026-119763changelog.com: missing authz exposes unpublished content5.30.5%—Oct 30CRITECVE-2026-119706LMDeploy: unauthenticated RCE via pickle in /update_weights9.81.0%lmdeployOct 30HIGHECVE-2026-119578MONAI: code execution via Auto3DSeg algo_object.json7.80.6%monaiOct 30MEDICVE-2026-119557n8n: Databricks node path traversal leaks secrets5.90.5%n8nOct 30HIGHCVE-2026-119408n8n: RCE via deprecated nodes bypassing task runner8.80.6%n8nOct 30MEDICVE-2026-114691libstdc++ (GCC): vector<bool> integer wrap causes DoS5.9—rhoai/odh-mlflow-operator-rhel9Oct 30MEDICVE-2026-114690GCC libstdc++: parallel search OOB access causes local DoS6.2—rhoai/odh-mlflow-operator-rhel9Oct 30MEDICVE-2026-118760Kubeflow Pipelines: missing authz exposes tenant artifacts6.50.4%—Oct 29CRITECVE-2026-93680Langflow: improper authentication allows remote bypass9.82.2%langflowOct 29MEDICVE-2026-90991Langflow: unbounded resource allocation enables DoS6.50.4%langflowOct 29MEDICVE-2026-77819Langflow: path traversal allows arbitrary file overwrite6.50.4%langflowOct 29MEDICVE-2026-77817Langflow: secrets exposed in flow/project exports6.50.3%langflowOct 29CRITCVE-2026-18894Langflow: public flow triggers stored Python code RCE9.80.5%langflowOct 29Frequently 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