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-2026-108783Amnezia-Web-Panel: default credentials in backup download7.30.4%Amnezia-Web-PanelOct 12MEDICVE-2026-19576Zephyr GT911: stack overflow via rogue touch controller6.80.2%—Oct 11MEDICVE-2026-108757Pinclaw: missing auth enables agent prompt injection6.50.2%openclawOct 11MEDICVE-2026-108752JupyterHub: OAuth client ID collision lets users hijack servers4.20.2%—Oct 11MEDICVE-2026-108748Quarkus LangChain4j: WebSocket memory leak enables DoS5.30.4%—Oct 11MEDIECVE-2026-108575LiteLLM: improper authorization in get_secret api_key6.30.2%LiteLLMOct 11MEDIECVE-2026-108574LiteLLM: IDOR in spend logs exposes session data4.30.2%LiteLLMOct 11MEDICVE-2026-108597Cohere SDK: tar slip in SageMaker S3 model extraction4.80.3%cohereOct 10MEDIECVE-2026-108554pdf2zh: unauthenticated SSRF via Link input5.30.3%pdf2zhOct 10MEDICVE-2026-107854Jexactyl: IDOR in billing endpoint allows renewing others' servers5.40.2%—Oct 9UNKNECVE-2026-107852Jexactyl: Stripe payment validation bypass allows underpayment—0.2%—Oct 9HIGHECVE-2026-108156LobsterAI: skill _meta.json path abuse deletes home dir7.10.2%—Oct 9HIGHCVE-2026-100227Apache CXF: XML signature wrapping bypass in JAX-RS7.50.3%—Oct 9UNKNCVE-2026-101998Docker Sandboxes: fail-open proxy leaks OAuth and API tokens—0.2%anthropicOct 8UNKNCVE-2026-103663Ollama: path traversal in /api/pull enables root RCE—0.7%ollamaOct 8HIGHCVE-2026-107161Cyrus SASL: DIGEST-MD5 heap overflow crashes RHOAI clients7.5—rhoai/odh-mlflow-operator-rhel9Oct 7HIGHCVE-2026-103435Claude Code: TOCTOU symlink race allows out-of-sandbox write—0.3%@anthropic-ai/claude-codeOct 7HIGHCVE-2026-97680Langflow: access control flaw in vertex cache leaks data8.30.3%langflowOct 7HIGHCVE-2026-97679Langflow: authenticated code injection allows RCE8.80.7%langflowOct 7HIGHCVE-2026-97678Langflow: authenticated RCE via improper input validation8.80.6%langflowOct 7Frequently 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