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:Date CVSS EPSS KEV first Most exploited

Filter:All Critical High MediumKEV only Active exploitationHas patch No patch

Latest AI Security Threats

Showing 20 of 4307 results

HIGHEXPLOIT AVAIL

pydantic-ai: SSRF allows internal network access

CVE-2026-25580

Data ExtractionAuth BypassFrameworkAgentAPI

pydantic-ai-slimPatch: 1.56.0CWE-9185126 ATLAS

pydantic-ai: Path Traversal enables file access

CVE-2026-25640

Code ExecutionData ExtractionFrameworkAgent

pydantic-ai-slimPatch: 1.51.0CWE-225125 ATLAS

MEDIUMEXPLOIT AVAIL

OpenClaw: path traversal enables arbitrary file read

CVE-2026-25475

Data ExtractionPrivacy ViolationSupply ChainAgentPlugin

openclawCWE-2235 ATLAS1 incident

n8n: Input Validation flaw enables exploitation

CVE-2026-21893

Code ExecutionSocial EngineeringAgentRAGAPI

n8nCWE-201610 ATLAS

n8n: Protection Bypass circumvents security controls

CVE-2026-25115

Code ExecutionAuth BypassData ExtractionAgentFrameworkPlugin

n8nCWE-693167 ATLAS

n8n: Arbitrary File Upload enables RCE

CVE-2026-25056

Code ExecutionAuth BypassData ExtractionAgentFrameworkPlugin

n8nCWE-434168 ATLAS

n8n: Path Traversal enables file access

CVE-2026-25055

Code ExecutionAuth BypassAgentFramework

n8nCWE-22167 ATLAS

n8n: XSS enables session hijacking

CVE-2026-25054

Auth BypassCode ExecutionData ExtractionAgentFrameworkAPI

n8nCWE-79167 ATLAS

n8n: Command Injection enables RCE

CVE-2026-25053

Code ExecutionData ExtractionAuth BypassAgentFrameworkPlugin

n8nCWE-78169 ATLAS

n8n: security flaw enables exploitation

CVE-2026-25052

Auth BypassData ExtractionData LeakageAgentFrameworkAPI

n8nCWE-367169 ATLAS

n8n: XSS enables session hijacking

CVE-2026-25051

Code ExecutionAuth BypassData ExtractionAgentFrameworkAPI

n8nCWE-79166 ATLAS

n8n: security flaw enables exploitation

CVE-2026-25049

Code ExecutionData ExtractionAuth BypassAgentFrameworkAPI

n8nCWE-913168 ATLAS

n8n: Info Disclosure leaks sensitive data

CVE-2025-61917

Data ExtractionData LeakagePrivacy ViolationAgentFrameworkAPI

n8nCWE-200165 ATLAS

sagemaker: security flaw enables exploitation

CVE-2026-1777

Code ExecutionData ExtractionSupply ChainFrameworkTraining Data

sagemakerPatch: 3.2.0CWE-201508 ATLAS

sagemaker: security flaw enables exploitation

CVE-2026-1778

Supply ChainCode ExecutionInferenceFramework

sagemakerPatch: 3.1.1CWE-295505 ATLAS

CRITICALEXPLOIT AVAILSCANNER

vllm: security flaw enables exploitation

CVE-2026-22778

Code ExecutionData LeakageInferenceFrameworkAPI

vllmCWE-532946 ATLAS

picklescan: Deserialization enables RCE

GHSA-m7j5-r2p5-c39r

Supply ChainDoSCode ExecutionFrameworkModelTraining Data

picklescanPatch: 1.0.1CWE-50234 ATLAS

picklescan: Deserialization enables RCE

GHSA-9m3x-qqw2-h32h

Supply ChainCode ExecutionModelFramework

picklescanPatch: 1.0.1CWE-50236 ATLAS

CRITICALEXPLOIT AVAIL

langroid: Code Injection enables RCE

CVE-2026-25481

Code ExecutionPrompt InjectionAuth BypassAgentFrameworkPlugin

langroidPatch: 0.59.32CWE-9446 ATLAS

libxml2 xmllint: memory leak in shell causes local DoS

CVE-2026-1757

rhoai/odh-mlflow-operator-rhel96951 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