AI Threat Alert

AI 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.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
4,330

AI/ML CVEs Tracked

535

Critical

107

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 4330 results
SeverityCVE IDSummaryCVSSEPSSPackageDate
HIGHECVE-2026-47237Kubeflow: token theft lets any user hijack accounts8.00.4%—Jul 21MEDIECVE-2026-58435Gitea: LFS deploy-key flaw leaks private repo objects5.40.3%code.gitea.io/giteaJul 21HIGHCVE-2026-15829MCP Toolbox: SQLi bypasses BigQuery allowedDatasets ACL—0.2%—Jul 21CRITECVE-2026-65007Grav CMS API plugin: forged keys enable account takeover9.60.3%—Jul 21MEDIECVE-2026-14185WPBot: missing auth check lets subscribers edit RAG config4.30.3%—Jul 21UNKNECVE-2026-57495AgenticMail: unauthenticated email hijacks AI agent—0.4%—Jul 20HIGHECVE-2026-54058Pillow: OOB read/DoS via unchecked mmap stride (McIdas)—0.5%pillowJul 20MEDICVE-2026-64650@ai-sdk/harness-codex: tool relay authz bypass—0.2%—Jul 20CRITECVE-2026-63766GPT-SoVITS: unauthenticated RCE via webui.py9.82.1%—Jul 20CRITECVE-2026-63767ktransformers: unauth pickle RCE via ZMQ socket9.81.1%ktransformersJul 20MEDICVE-2026-46671onenote_parser: path traversal via crafted .onetoc2 file4.40.2%—Jul 20MEDIECVE-2026-15588GLib GDBus: unbounded auth line enables local DoS5.30.5%rhaiis/vllm-cuda-rhel9Jul 20HIGHECVE-2026-12484Keras: unsafe pickle deserialization allows RCE7.80.3%kerasJul 19UNKNECVE-2026-12228Lollms: stored XSS in prompt-share DM inbox—0.3%parisneo/lollmsJul 18HIGHCVE-2026-50272dd-trace: unbounded W3C baggage parsing enables DoS7.50.8%—Jul 17HIGHCVE-2026-50271dd-trace-py: unbounded baggage header parsing causes DoS7.50.8%—Jul 17CRITCVE-2026-13446Langflow: hard-coded credentials enable takeover9.80.4%langflowJul 17HIGHCVE-2026-13445Langflow: SaveToFile flaw breaks user storage isolation8.10.4%langflowJul 17CRITCVE-2026-8859Langflow: path traversal writes arbitrary files9.90.6%langflowJul 17CRITCVE-2026-8635Langflow: DB manipulation escalates to superuser RCE9.90.6%langflowJul 17

Frequently 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