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
3,628

AI/ML CVEs Tracked

484

Critical

101

New This Week

25

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 2356 results — no patch
MEDIUM

Linux Kernel KVM: nSVM VMEXIT host state corruption

CVE-2026-46032
5.5
EPSS 0.1%
Code Execution DoS Inference
2 ATLAS
MEDIUM

Linux mlx5: RDMA hang DoS on AI training clusters

CVE-2026-45973
5.5
EPSS 0.2%
DoS Inference
2 ATLAS
MEDIUM

Linux mlx5e: deadlock DoS in Mellanox NIC recovery paths

CVE-2026-45907
5.5
EPSS 0.1%
DoS Inference Model
2 ATLAS
MEDIUM

IBM Db2 APM: DoS via query special element injection

CVE-2026-3676
6.5
EPSS 0.4%
DoS Framework Inference
CWE-1284 3 ATLAS
HIGH

NVIDIA Transformers4Rec: deserialization RCE

CVE-2026-24162
7.8
EPSS 0.4%
Code Execution Supply Chain Data Extraction Framework Model
CWE-502 4 ATLAS
MEDIUM EXPLOIT AVAIL

vllm: unauthenticated DoS in OpenAI-compatible serving path

CVE-2026-9540
5.3
EPSS 0.4%
DoS Inference API
vllm CWE-404 92 3 ATLAS
MEDIUM EXPLOIT AVAIL

cline-mcp-memory-bank: path traversal in memory init

CVE-2026-9468
6.3
EPSS 0.3%
Data Extraction Code Execution Agent Plugin
CWE-22 5 ATLAS
MEDIUM EXPLOIT AVAIL

Notebook Pro: DoS via oversized notebook name input

CVE-2018-25378
6.2
EPSS 0.1%
DoS Framework
CWE-789 2 ATLAS
CRITICAL EXPLOIT AVAIL

MLflow: auth bypass on artifact uploads enables RCE

CVE-2026-2651
9.0
EPSS 0.3%
Supply Chain Auth Bypass Code Execution Model Inference Framework
mlflow/mlflow CWE-862 690 4 ATLAS
HIGH

389-ds-base: LDAP DoS via unbounded control count

CVE-2026-9064
7.5
EPSS 0.8%
DoS Framework
3 ATLAS
CRITICAL

guardrails-ai: malicious 0.10.1 enables host compromise

CVE-2026-45758
9.6
EPSS 0.3%
Supply Chain Code Execution Framework Agent
guardrails-ai CWE-506 78 5 ATLAS
LOW

Mistral npm SDK: supply chain attack, no impact

GHSA-jgg6-4rpr-wfh7
--
Supply Chain Code Execution API
@mistralai/mistralai-azure CWE-506 492 5 ATLAS
CRITICAL

mistralai 2.4.6: supply chain dropper executes on import

GHSA-wx9m-wx4f-4cmg
9.6
Supply Chain Code Execution API Framework
mistralai CWE-506 492 6 ATLAS
CRITICAL EXPLOIT AVAIL

ChromaDB: pre-auth RCE via trust_remote_code injection

CVE-2026-45829
10.0
EPSS 12.4%
Code Execution Auth Bypass Supply Chain RAG Framework Agent
chromadb CWE-94 1.5K 6 ATLAS
HIGH

gnutls: DTLS packet-reorder bug DoS hits AI inference servers

CVE-2026-42009
7.5
EPSS 1.3%
DoS Inference
rhaiis/vllm-rocm-rhel9 92 2 ATLAS
HIGH EXPLOIT AVAIL

Bert-VITS2: path traversal exposes ML training filesystem

CVE-2026-8756
7.3
EPSS 0.5%
Data Extraction Code Execution Framework Training Data
CWE-22 4 ATLAS
CRITICAL EXPLOIT AVAIL

Crabbox: env-var allowlist leaks secrets to remote exec

CVE-2026-8634
9.1
EPSS 0.7%
Supply Chain Code Execution Data Leakage Agent Framework
crabbox 3 5 ATLAS
HIGH EXPLOIT AVAIL

Crabbox: IDOR lets viewers hijack Code/VNC/Egress

CVE-2026-8629
8.1
EPSS 0.3%
Auth Bypass Code Execution Agent
crabbox 3 3 ATLAS
HIGH

Crabbox: header spoofing bypasses lease auth

CVE-2026-8621
8.8
EPSS 0.4%
Auth Bypass Privacy Violation Agent API
crabbox 3 3 ATLAS
HIGH EXPLOIT AVAIL

nnU-Net: prompt injection hijacks CI/CD triage agent

CVE-2026-44246
7.2
EPSS 0.2%
Prompt Injection Code Execution Agent Plugin
claude-code 5 ATLAS

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