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

CRITICALEXPLOIT AVAIL

cai-framework: Command Injection enables RCE

CVE-2025-67511

Code ExecutionPrompt InjectionAgentFramework

1Panel: CSRF allows unauthorized panel rename

CVE-2025-34430

Auth BypassSocial EngineeringAPI

1Panel: CSRF in username change enables lockout

CVE-2025-34410

DoSAuth BypassInference

langgraph-checkpoint-sqlite: SQL Injection exposes database

CVE-2025-67644

Auth BypassData ExtractionFrameworkAgent

langgraph-checkpoint-sqlitePatch: 3.0.1CWE-894.1K4 ATLAS

NVIDIA: Deserialization enables RCE

CVE-2025-33213

Code ExecutionSupply ChainData ExtractionFrameworkTraining DataModel

HIGHEXPLOIT AVAIL

n8n: security flaw enables exploitation

CVE-2025-65964

Code ExecutionSupply ChainAgentFramework

MEDIUMEXPLOIT AVAIL

AI component: SQL Injection exposes database

CVE-2025-13922

Data ExtractionAuth BypassPluginAPI

langflow: security flaw enables exploitation

CVE-2025-34291

Auth BypassCode ExecutionFrameworkAgent

langflowCWE-3468 ATLAS

HIGHEXPLOIT AVAIL

open-webui: SSRF allows internal network access

CVE-2025-65958

Data ExtractionData LeakageCode ExecutionAPIRAG

open-webuiPatch: 0.6.37CWE-91826 ATLAS

Anthropic: Protection Bypass circumvents security controls

CVE-2025-66479

Auth BypassCode ExecutionData ExtractionAgentFrameworkAPI

LOWEXPLOIT AVAIL

open-webui: Access Control bypass enables privilege escalation

CVE-2025-63681

Auth BypassDoSAPIInferenceFramework

open-webuiCWE-28424 ATLAS

HIGHEXPLOIT AVAIL

mcp-server-kubernetes: Command Injection enables RCE

CVE-2025-66404

Code ExecutionPrompt InjectionAuth BypassAgentPluginFramework

taxopress: SQL Injection exposes database

CVE-2025-13359

Data ExtractionPrivacy ViolationPluginAPI

taxopress: Missing Auth allows unauthorized operations

CVE-2025-13354

Auth BypassPluginAPI

vllm: Code Injection enables RCE

CVE-2025-66448

Supply ChainCode ExecutionFrameworkInferenceModel

vllmCWE-94948 ATLAS

UNKNOWNEXPLOIT AVAIL

Keras: Path Traversal enables file access

CVE-2025-12638

Supply ChainCode ExecutionFrameworkTraining Data

ray: security flaw enables exploitation

CVE-2025-34351

Auth BypassCode ExecutionModel PoisoningFrameworkTraining DataInference

rayCWE-3046428 ATLAS

CRITICALKEVSCANNER

ray: Code Injection enables RCE

CVE-2025-62593

Code ExecutionAuth BypassSocial EngineeringFramework

rayPatch: 2.52.0CWE-946428 ATLAS

langchain-core: security flaw enables exploitation

CVE-2025-65106

Prompt InjectionCode ExecutionData ExtractionFrameworkAgent

langchain-corePatch: 1.0.7CWE-13366.3K7 ATLAS

HIGHEXPLOIT AVAIL

mlx: security flaw enables exploitation

CVE-2025-62609

DoSSupply ChainFrameworkModel

mlxCWE-4764295 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