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 544 results — Medium severity, has patch
MEDIUMEXPLOIT AVAIL

kedro-datasets: path traversal enables arbitrary file write

CVE-2026-35492
6.5
EPSS 0.4%
Supply ChainModel PoisoningCode ExecutionFrameworkTraining Data
kedro-datasetsPatch: 9.3.0CWE-222.8K3 ATLAS
MEDIUM

vLLM: OOM DoS via unbounded video frame decoding

CVE-2026-34755
6.5
EPSS 0.5%
DoSFrameworkInferenceAPI
vllmPatch: 0.19.0CWE-770943 ATLAS
MEDIUM

vLLM: SSRF in batch API exposes cloud metadata endpoints

CVE-2026-34753
5.4
EPSS 0.3%
Data ExtractionAuth BypassFrameworkInference
vllmPatch: 0.19.0CWE-918945 ATLAS
MEDIUM

ltiauthenticator: OAuth nonce leak causes server DoS

CVE-2026-34052
5.9
EPSS 0.3%
DoSFramework
jupyterhub-ltiauthenticatorPatch: 1.6.3CWE-4011.9K3 ATLAS
MEDIUM

JupyterHub: open redirect enables post-login phishing

CVE-2026-33709
--
EPSS 0.2%
Social EngineeringAuth BypassFramework
jupyterhubPatch: 5.4.4CWE-6011.9K4 ATLAS
MEDIUM

vLLM: DoS via unbounded n parameter causes OOM crash

CVE-2026-34756
6.5
EPSS 0.4%
DoSInferenceAPI
vllmPatch: 0.19.0CWE-770944 ATLAS
MEDIUM

OpenClaw: SSRF in marketplace fetch hits internal AI infra

GHSA-9q7v-8mr7-g23p
--
Supply ChainData ExtractionAuth BypassPluginInferenceAgent
openclawPatch: 2026.3.31CWE-91834 ATLAS
MEDIUMEXPLOIT AVAIL

ONNX: symlink traversal reads host files via model loading

CVE-2026-34447
5.5
EPSS 0.3%
Supply ChainData ExtractionFrameworkModel
onnxPatch: 1.21.0CWE-221.1K5 ATLAS
MEDIUM

ONNX: hardlink path traversal leaks sensitive files

CVE-2026-34446
4.7
EPSS 0.2%
Supply ChainData ExtractionFrameworkModel
onnxPatch: 1.21.0CWE-221.1K4 ATLAS
MEDIUM

Anthropic SDK: TOCTOU symlink escape in async memory tool

CVE-2026-34452
--
EPSS 0.1%
Code ExecutionData ExtractionAuth BypassFrameworkAgentAPI
anthropicPatch: 0.87.0CWE-596.3K5 ATLAS17 incidents
MEDIUM

anthropic-ai/sdk: memory tool path traversal escape

CVE-2026-34451
--
EPSS 0.4%
Prompt InjectionData ExtractionCode ExecutionFrameworkAgentAPI
@anthropic-ai/sdkPatch: 0.81.0CWE-222216 ATLAS
MEDIUM

anthropic-sdk: insecure file perms expose agent memory

CVE-2026-34450
--
EPSS 0.1%
Data LeakageModel PoisoningData ExtractionAgentFrameworkAPI
anthropicPatch: 0.87.0CWE-2766.3K4 ATLAS17 incidents
MEDIUM

OpenClaw: HTTP scope bypass enables model enumeration

GHSA-68f8-9mhj-h2mp
--
Auth BypassData ExtractionAPIInference
openclawPatch: 2026.3.24CWE-28434 ATLAS2 incidents
MEDIUM

openclaw: webhook rate-limit bypass enables token brute-force

CVE-2026-35646
4.8
EPSS 0.2%
Auth BypassData ExtractionAgentPlugin
openclawPatch: 2026.3.28CWE-30734 ATLAS1 incident
MEDIUM

openclaw: unauthenticated webhook parsing enables DoS

CVE-2026-35640
5.3
EPSS 0.4%
DoSAgent
openclawPatch: 2026.3.28CWE-40033 ATLAS
MEDIUM

openclaw: auth bypass exposes agent session history via HTTP

CVE-2026-35657
6.5
EPSS 0.2%
Auth BypassData ExtractionAgentAPI
openclawPatch: 2026.3.25CWE-63933 ATLAS1 incident
MEDIUM

n8n: stored XSS via malicious OAuth2 Authorization URL

GHSA-364x-8g5j-x2pr
5.4
Code ExecutionData ExtractionSocial EngineeringAgentFrameworkPlugin
n8nPatch: 2.8.0CWE-79167 ATLAS
MEDIUM

n8n: Stored XSS in Chat Trigger via CSS injection

GHSA-3c7f-5hgj-h279
5.4
Code ExecutionData ExtractionAgentFramework
n8nPatch: 1.123.27CWE-79166 ATLAS
MEDIUM

n8n: stored XSS enables phishing via Form Node

GHSA-w673-8fjw-457c
4.1
Social EngineeringData ExtractionAgentFramework
n8nPatch: 2.12.0CWE-79164 ATLAS
MEDIUM

n8n: Stored XSS in Form Trigger enables phishing

GHSA-q4fm-pjq6-m63g
5.4
Social EngineeringData ExtractionAgentFramework
n8nPatch: 2.11.2CWE-79164 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