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
4,307

AI/ML CVEs Tracked

533

Critical

96

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 2876 results — no patch
SeverityCVE IDSummaryCVSSEPSSPackageDate
HIGHCVE-2026-104335Langflow OSS: improper access control enables RCE8.80.9%Langflow OSSOct 6HIGHECVE-2026-86540Knowns: untrusted LSP binary path allows code execution7.80.2%—Oct 6MEDICVE-2026-105922vLLM: penalty handler flaw allows remote DoS4.30.3%vllmOct 6MEDIECVE-2026-105775vLLM: OOB read in Mamba2 mixer enables remote DoS4.30.3%vLLMOct 6HIGHECVE-2026-102826simple-git: command injection via git clone config bypass8.10.5%—Oct 5MEDIGHSA-g7fw-3gjp-g5hfOpenClaw channels: allowlist bypass exposes chat reads6.5—openclawOct 5HIGHECVE-2026-105786Joplin Server: app-auth flaw enables account takeover—0.4%—Oct 5HIGHECVE-2026-105759vLLM: unbounded metrics labels allow memory-exhaustion DoS7.50.4%vllmOct 5MEDIECVE-2026-105785Joplin Server: reset-token reuse enables account takeover4.80.2%—Oct 5MEDIECVE-2026-105784Joplin: CSS injection via jsoncanvas note rendering4.60.2%—Oct 5HIGHECVE-2026-105783Joplin: Web Clipper CORS flaw leaks permanent API token8.00.1%—Oct 5CRITECVE-2026-105740Langflow: MCP Stdio command injection gives authenticated RCE9.93.9%langflowOct 5HIGHCVE-2026-105115OpenAM: unauthenticated class instantiation via JAX-RPC8.60.5%—Oct 3HIGHCVE-2026-104478Formwork: path traversal in backups reads/deletes files7.10.4%—Oct 2MEDIGHSA-p23f-cm6q-2qp8SiYuan MCP: asset.upload reads arbitrary host files5.7——Oct 2CRITGHSA-jqmf-mx4f-hfr6Vibe-Trading: unauth agent RCE via shell tools, exec10.0——Oct 2HIGHCVE-2026-104873LangGraph SDK: auth decorator flaw enables cross-user access—0.3%langgraphOct 2CRITCVE-2026-104019SageMaker Distribution: OS command injection exposes IAM creds9.01.4%sagemakerOct 2MEDIECVE-2026-103763SiYuan: info disclosure via getNotebookInfo endpoint5.80.3%—Oct 2MEDIECVE-2026-103762SiYuan: missing authz leaks hidden notebook IDs5.30.3%—Oct 2

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