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
2,404

AI/ML CVEs Tracked

347

Critical

310

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 1033 results — High severity
HIGH

PraisonAI: RCE via ungated exec_module in agent config

CVE-2026-47398
8.1
EPSS 0.1%
Code Execution Supply Chain Agent Framework
PraisonAI Patch: 4.6.40 CWE-94 1 5 ATLAS
HIGH

OpenClaw: scope bypass enables full agent admin takeover

CVE-2026-35674
8.8
EPSS 0.3%
Auth Bypass Code Execution Supply Chain Agent Plugin
openclaw CWE-863 4 5 ATLAS
HIGH

OpenClaw: auth bypass enables unauthorized agent approval

CVE-2026-35630
8.0
EPSS 0.2%
Auth Bypass Code Execution Agent Plugin
openclaw CWE-862 4 4 ATLAS
HIGH

OpenClaw: auth bypass enables persistent device enrollment

CVE-2026-32905
8.3
EPSS 0.2%
Auth Bypass Code Execution Agent Plugin
openclaw CWE-862 4 4 ATLAS
HIGH EXPLOIT AVAIL

Froxlor: symlink-following grants customer root SSH access

CVE-2026-41236
8.8
EPSS 0.4%
Auth Bypass Code Execution Inference Framework
froxlor/froxlor Patch: 2.3.7 CWE-59 479 4 ATLAS
HIGH EXPLOIT AVAIL

Froxlor: shell whitelist bypass grants host shell access

CVE-2026-41235
--
EPSS 0.2%
Auth Bypass Code Execution API Inference
froxlor/froxlor Patch: 2.3.7 CWE-863 479 4 ATLAS
HIGH

Linux kernel RDMA/mlx4: RCU race may crash ML training nodes

CVE-2026-46181
7.8
EPSS 0.1%
DoS Framework
1 ATLAS
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
HIGH

Kirby CMS: Stored XSS via javascript: URI scheme bypass

CVE-2026-45368
--
EPSS 0.1%
Code Execution Auth Bypass Social Engineering Framework Plugin
getkirby/cms Patch: 4.9.1 CWE-79 479 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
HIGH

Kirby CMS: stored XSS in list field enables session hijack

CVE-2026-44175
--
EPSS 0.0%
Code Execution Auth Bypass API
getkirby/cms Patch: 4.9.1 CWE-79 479 4 ATLAS
HIGH

Kirby: unsafe reflection allows privilege escalation

CVE-2026-44174
--
EPSS 0.1%
Auth Bypass Data Extraction Code Execution API Framework
getkirby/cms Patch: 4.9.1 CWE-470 479 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
HIGH EXPLOIT AVAIL

LiteLLM: privilege escalation to proxy_admin via /user/update

CVE-2026-47102
8.8
EPSS 0.4%
Auth Bypass Data Extraction Inference API
litellm Patch: 1.83.10 CWE-863 6 5 ATLAS
HIGH EXPLOIT AVAIL

LiteLLM: RBAC bypass enables proxy admin escalation

CVE-2026-47101
8.8
EPSS 0.5%
Auth Bypass Data Extraction API Inference Framework
litellm Patch: 1.83.14 CWE-863 6 5 ATLAS
HIGH EXPLOIT AVAIL

mcp-server-kubernetes: auth bypass enables full cluster RCE

CVE-2026-46519
8.8
EPSS 0.4%
Auth Bypass Code Execution Agent Plugin
mcp-server-kubernetes Patch: 3.6.0 CWE-863 1 5 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

SageMaker SDK: cleartext HMAC key enables model artifact RCE

CVE-2026-8596
7.2
EPSS 0.4%
Data Leakage Code Execution Supply Chain Inference Model Framework
sagemaker Patch: 2.257.2 CWE-312 51 4 ATLAS
HIGH EXPLOIT AVAIL

lmdeploy: hardcoded trust_remote_code enables RCE

CVE-2026-46432
7.8
EPSS 0.1%
Supply Chain Code Execution Inference Model Framework
lmdeploy Patch: 0.13.0 CWE-94 8.3K 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