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

95

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 1961 results — Active exploitation
MEDIUMEXPLOIT AVAIL

local-deep-research: SSRF via URL parser differential bypass

CVE-2026-46526
5.0
EPSS 0.3%
Auth BypassData ExtractionAgent
local-deep-researchPatch: 1.6.10CWE-9183 ATLAS
UNKNOWNEXPLOIT AVAIL

vllm: trust_remote_code bypass enables RCE via HuggingFace

CVE-2026-4944
--
EPSS 0.7%
Supply ChainCode ExecutionInferenceModel
vllmCWE-22945 ATLAS
CRITICALEXPLOIT AVAIL

langroid: Prompt-to-SQL injection enables RCE on DB host

CVE-2026-25879
9.8
EPSS 0.6%
Prompt InjectionCode ExecutionData ExtractionAgentFramework
langroidPatch: 0.63.0CWE-8946 ATLAS
MEDIUMEXPLOIT AVAIL

Gradio: cookie injection hijacks cross-Space sessions

CVE-2026-48545
6.8
EPSS 0.4%
Auth BypassPrivacy ViolationData LeakageInferenceFramework
gradioPatch: 6.15.0CWE-3847353 ATLAS
HIGHEXPLOIT AVAIL

Langflow: DoS via uncontrolled resource consumption

CVE-2026-7528
7.5
EPSS 0.3%
DoSFramework
langflowCWE-4003 ATLAS
MEDIUMEXPLOIT AVAIL

vllm: unauthenticated DoS in OpenAI-compatible serving path

CVE-2026-9540
5.3
EPSS 0.4%
DoSInferenceAPI
vllmCWE-404943 ATLAS
MEDIUMEXPLOIT AVAIL

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

CVE-2026-9468
6.3
EPSS 0.3%
Data ExtractionCode ExecutionAgentPlugin
CWE-225 ATLAS
MEDIUMEXPLOIT AVAIL

Notebook Pro: DoS via oversized notebook name input

CVE-2018-25378
6.2
EPSS 0.1%
DoSFramework
CWE-7892 ATLAS
CRITICALEXPLOIT AVAIL

MLflow: auth bypass on artifact uploads enables RCE

CVE-2026-2651
9.0
EPSS 0.3%
Supply ChainAuth BypassCode ExecutionModelInferenceFramework
mlflow/mlflowCWE-8626954 ATLAS
CRITICALEXPLOIT AVAIL

Boxlite: read-only bypass enables host code execution

CVE-2026-46695
10.0
EPSS 0.3%
Code ExecutionSupply ChainData LeakageAgentFramework
boxlite-cliPatch: 0.9.0CWE-2844 ATLAS
HIGHEXPLOIT AVAIL

LiteLLM: privilege escalation to proxy_admin via /user/update

CVE-2026-47102
8.8
EPSS 0.7%
Auth BypassData ExtractionInferenceAPI
litellmPatch: 1.83.10CWE-86365 ATLAS
HIGHEXPLOIT AVAIL

LiteLLM: RBAC bypass enables proxy admin escalation

CVE-2026-47101
8.8
EPSS 1.2%
Auth BypassData ExtractionAPIInferenceFramework
litellmPatch: 1.83.14CWE-86365 ATLAS
HIGHEXPLOIT AVAIL

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

CVE-2026-46519
8.8
EPSS 0.5%
Auth BypassCode ExecutionAgentPlugin
mcp-server-kubernetesPatch: 3.6.0CWE-86315 ATLAS
HIGHEXPLOIT AVAIL

LMDeploy: hardcoded trust_remote_code enables RCE

CVE-2026-46517
7.8
EPSS 0.2%
Supply ChainCode ExecutionInferenceFramework
lmdeployPatch: 0.13.0CWE-9415 ATLAS
HIGHEXPLOIT AVAIL

lmdeploy: hardcoded trust_remote_code enables RCE

CVE-2026-46432
7.8
EPSS 0.1%
Supply ChainCode ExecutionInferenceModelFramework
lmdeployPatch: 0.13.0CWE-949.8K5 ATLAS
MEDIUMEXPLOIT AVAIL

MLflow: missing authz exposes all model versions

CVE-2026-2734
6.5
EPSS 0.4%
Auth BypassData ExtractionPrivacy ViolationFrameworkModel
mlflowPatch: 3.10.0CWE-2846954 ATLAS
HIGHEXPLOIT AVAIL

diffusers: TOCTOU race bypasses trust_remote_code, RCE

CVE-2026-45804
7.5
EPSS 0.4%
Supply ChainCode ExecutionFrameworkModel
diffusersPatch: 0.38.0CWE-3674045 ATLAS
CRITICALEXPLOIT AVAILSCANNER

9router: unauthenticated RCE exposes LLM API keys

CVE-2026-46339
10.0
EPSS 2.8%
Auth BypassCode ExecutionData ExtractionPluginAPIAgent
9routerPatch: 0.4.37CWE-781.9K8 ATLAS
CRITICALEXPLOIT AVAIL

MLflow: cross-origin bypass enables RCE via AI agent

CVE-2026-2611
9.6
EPSS 0.4%
Auth BypassCode ExecutionAgentFramework
mlflowPatch: 3.10.0CWE-3466955 ATLAS
HIGHEXPLOIT AVAIL

MLflow: insecure tmp dir perms enable model artifact RCE

CVE-2026-4137
7.0
EPSS 0.2%
Code ExecutionSupply ChainFrameworkModel
mlflowPatch: 3.11.0CWE-3786954 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