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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 4331 results
CRITICAL

Oracle Coherence: unauthenticated HTTPS takeover

CVE-2026-35304
9.8
EPSS 0.5%
Auth BypassCode ExecutionData ExtractionAPIInferenceFramework
coherence3804 ATLAS
MEDIUM

vLLM: image metadata mishandling corrupts multimodal inputs

CVE-2026-12491
4.8
EPSS 0.2%
Adversarial ExamplesDoSInferenceModel
rhaiis/vllm-cpu-rhel9944 ATLAS
HIGH

WPBot Pro: subscriber file deletion → system DoS

CVE-2025-60223
7.7
EPSS 0.4%
DoSAuth BypassPlugin
wpbot-pro3 ATLAS
LOW

pi-coding-agent: XSS in HTML exports via prompt injection

CVE-2026-54326
2.5
EPSS 0.2%
Prompt InjectionCode ExecutionAgent
CWE-794 ATLAS
LOW

Nuxt: NoScript XSS enables script execution in head

GHSA-m3q2-p4fw-w38m
--
Code ExecutionData ExtractionAuth BypassFrameworkAPI
nuxtPatch: 4.4.7CWE-796.3K3 ATLAS
CRITICALSCANNER

LiteLLM: auth bypass via Host header spoofing

CVE-2026-49468
8.1
EPSS 3.0%
Auth BypassData ExtractionInferenceAPI
litellmPatch: 1.84.0CWE-29064 ATLAS
CRITICAL

backpropagate: auth bypass exposes LLM training plane

CVE-2026-48797
--
EPSS 0.3%
Auth BypassData ExtractionDoSTraining DataModelFramework
backpropagatePatch: 1.2.0CWE-3582.8K6 ATLAS
UNKNOWN

n8n: credential exfiltration via SecurityScorecard SSRF node

CVE-2026-54304
--
EPSS 0.4%
Data LeakageAuth BypassAgentPlugin
n8nPatch: 1.123.55CWE-200165 ATLAS
UNKNOWN

n8n: MCP browser auth bypass allows full browser takeover

CVE-2026-54309
--
EPSS 0.5%
Auth BypassCode ExecutionData ExtractionAgentPlugin
n8nPatch: 2.26.2CWE-306164 ATLAS
UNKNOWN

n8n: IDOR enables OAuth credential hijack in agent workflows

CVE-2026-54305
--
EPSS 0.4%
Auth BypassData ExtractionPrivacy ViolationAgentPluginFramework
n8nPatch: 1.123.55CWE-284166 ATLAS
UNKNOWN

n8n: credential hijack via partial authorization bypass

CVE-2026-54307
--
EPSS 0.4%
Auth BypassData ExtractionPrivacy ViolationAgentFramework
n8nPatch: 1.123.55CWE-863165 ATLAS
MEDIUM

n8n: decompression bomb DoS via public webhook

CVE-2026-54314
--
EPSS 0.5%
DoSAgentFramework
n8nPatch: 2.24.0CWE-409164 ATLAS
MEDIUM

pydantic-ai: SSRF IPv6 bypass exposes cloud IAM creds

CVE-2026-48782
6.8
EPSS 0.4%
Data ExtractionAuth BypassAgentFramework
pydantic-aiPatch: 1.102.0CWE-9185124 ATLAS
MEDIUM

n8n: read-only users can trigger workflow execution via API

GHSA-h3jj-5f3v-3685
6.4
Auth BypassAgent
n8nPatch: 2.26.2CWE-863163 ATLAS
MEDIUM

n8n: AST bypass leaks env vars in Python Task Runner

GHSA-jwm3-qcfw-c5pp
5.0
Data LeakageCode ExecutionAuth BypassAgentFramework
n8nPatch: 2.26.2CWE-693165 ATLAS
UNKNOWN

n8n: stored XSS in Chat Trigger enables session hijack

CVE-2026-54302
--
EPSS 0.2%
Code ExecutionData ExtractionAuth BypassAgentFrameworkPlugin
n8nPatch: 1.123.55CWE-79165 ATLAS
MEDIUM

n8n: reflected XSS in trigger nodes enables session hijack

CVE-2026-54303
--
EPSS 0.2%
Social EngineeringAuth BypassData ExtractionAgentFrameworkPlugin
n8nPatch: 2.24.0CWE-79164 ATLAS
UNKNOWN

n8n: prototype pollution renders instance non-functional

CVE-2026-54312
--
EPSS 0.4%
DoSCode ExecutionAgentFrameworkPlugin
n8nPatch: 2.24.0CWE-1321164 ATLAS
MEDIUM

LangGraph SDK: path traversal bypasses proxy-layer authz

CVE-2026-48776
4.2
EPSS 0.2%
Auth BypassData ExtractionFrameworkAgent
langchain-aiCWE-223.2K3 ATLAS
CRITICAL

Oracle APM: unauthenticated write/DoS via JVM Diagnostics

CVE-2026-46858
9.1
EPSS 0.4%
Auth BypassDoSData ExtractionInferenceFramework
APM - Application Performance Management4 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