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
2,409

AI/ML CVEs Tracked

347

Critical

298

New This Week

18

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 1581 results — no patch
HIGH

Linux mlx4 RDMA: resource leak on SRQ creation error

CVE-2026-46178
7.8
EPSS 0.1%
DoS Inference
1 ATLAS
HIGH

Linux mlx5 RDMA: use-after-free in SRQ init path

CVE-2026-46176
7.8
EPSS 0.1%
Code Execution Inference Framework
2 ATLAS
UNKNOWN

CTI Transmute: stored XSS in notification panel

CVE-2026-9806
--
EPSS 0.3%
Code Execution Data Leakage Auth Bypass Framework API
4 ATLAS
MEDIUM EXPLOIT AVAIL

Gradio: cookie injection hijacks cross-Space sessions

CVE-2026-48545
6.8
EPSS 0.4%
Auth Bypass Privacy Violation Data Leakage Inference Framework
gradio CWE-384 685 3 ATLAS
HIGH EXPLOIT AVAIL

Langflow: DoS via uncontrolled resource consumption

CVE-2026-7528
7.5
EPSS 0.2%
DoS Framework
langflow CWE-400 3 ATLAS
CRITICAL

Langflow: RCE via symlink traversal in archive extraction

CVE-2026-7524
9.8
EPSS 0.6%
Code Execution Supply Chain Framework Agent
langflow CWE-22 4 ATLAS
MEDIUM

Linux Kernel: DMA coherency flaw in igorplugusb driver

CVE-2026-46091
5.5
EPSS 0.2%
DoS Inference
1 ATLAS
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-404 130 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
HIGH

LMDeploy: hardcoded trust_remote_code enables RCE

CVE-2026-46517
7.8
EPSS 0.1%
Supply Chain Code Execution Inference Framework
lmdeploy CWE-94 130 5 ATLAS
HIGH

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

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

@apify/actors-mcp-server: URL bypass → LLM prompt injection

CVE-2026-46341
6.1
EPSS 0.0%
Prompt Injection Auth Bypass Agent Plugin
CWE-20 5 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 7 5 ATLAS
LOW

Mistral npm SDK: supply chain attack, no impact

GHSA-jgg6-4rpr-wfh7
--
Supply Chain Code Execution API
@mistralai/mistralai-azure CWE-506 736 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