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
HIGHEXPLOIT AVAIL

OAI CN5G AMF: unauthenticated JSON DoS on 5G SBI interface

CVE-2025-66786
7.5
EPSS 0.4%
DoSAPIInference
oai-cn5g-amf15.6K3 ATLAS
HIGHEXPLOIT AVAIL

OAI CN5G AMF: Unauthenticated buffer overflow, RCE/DoS

CVE-2025-65805
7.5
EPSS 0.4%
DoSCode ExecutionInferenceAPI
oai-cn5g-amf15.6K3 ATLAS
MEDIUMEXPLOIT AVAIL

monai: Path Traversal enables file access

CVE-2026-21851
5.3
EPSS 0.4%
Supply ChainCode ExecutionFramework
monaiPatch: 1.5.2CWE-221284 ATLAS
MEDIUMEXPLOIT AVAIL

AI component: Missing Auth allows unauthorized operations

CVE-2025-14371
4.3
EPSS 0.2%
Auth BypassPluginAPI
CWE-8624 ATLAS
HIGHEXPLOIT AVAIL

mcp_typescript_sdk: security flaw enables exploitation

CVE-2026-0621
7.5
EPSS 0.4%
DoSFrameworkAPIAgent
@modelcontextprotocol/sdkPatch: 1.25.2CWE-13336.3K4 ATLAS
CRITICALEXPLOIT AVAILSCANNER

langflow: Missing Auth allows unauthenticated access

CVE-2026-21445
9.1
EPSS 33.3%
Auth BypassData ExtractionPrivacy ViolationFrameworkAgentAPI
langflowCWE-3067 ATLAS
CRITICALEXPLOIT AVAIL

n8n: Protection Bypass circumvents security controls

CVE-2025-68668
9.9
EPSS 13.2%
Code ExecutionAuth BypassAgentFrameworkPlugin
n8n166 ATLAS
HIGHEXPLOIT AVAIL

lmdeploy: Deserialization enables RCE

CVE-2025-67729
8.8
EPSS 0.5%
Supply ChainCode ExecutionFrameworkModelInference
lmdeployPatch: 0.11.1CWE-50216 ATLAS
CRITICALEXPLOIT AVAIL

langchain.js: Deserialization enables RCE

CVE-2025-68665
9.1
EPSS 0.8%
Supply ChainCode ExecutionData ExtractionFrameworkAgent
langchain.js3.2K5 ATLAS
HIGHEXPLOIT AVAIL

langchain-core: Deserialization enables RCE

CVE-2025-68664
8.2
EPSS 42.9%
Supply ChainCode ExecutionData ExtractionFrameworkAgent
langchain_coreCWE-5023.2K6 ATLAS
MEDIUMEXPLOIT AVAIL

local-deep-research: SSRF allows internal network access

CVE-2025-67743
6.3
EPSS 0.3%
Data ExtractionAuth BypassFrameworkAPI
local-deep-researchPatch: 1.3.9CWE-9184 ATLAS
HIGHKEVSCANNER

n8n: security flaw enables exploitation

CVE-2025-68613
8.8
EPSS 99.0%
Code ExecutionAuth BypassData ExtractionAgentFrameworkPlugin
n8nCWE-913169 ATLAS
HIGHEXPLOIT AVAIL

langflow: File Control enables path manipulation

CVE-2025-68478
7.1
EPSS 5.8%
Code ExecutionAuth BypassFrameworkAgent
langflowCWE-735 ATLAS
MEDIUMEXPLOIT AVAIL

langflow: SSRF allows internal network access

CVE-2025-68477
6.5
EPSS 6.3%
Data ExtractionAuth BypassPrivacy ViolationFrameworkAgentAPI
langflowCWE-9188 ATLAS
HIGHEXPLOIT AVAIL

nbconvert: security flaw enables exploitation

CVE-2025-53000
--
EPSS 0.3%
Code ExecutionSupply ChainFramework
CWE-4274 ATLAS
HIGHEXPLOIT AVAIL

fickling: Code Injection enables RCE

CVE-2025-67748
--
EPSS 0.3%
Supply ChainCode ExecutionFrameworkModel
ficklingPatch: 0.1.6CWE-94625 ATLAS
HIGHEXPLOIT AVAIL

fickling: Allowlist Bypass evades input filtering

CVE-2025-67747
--
EPSS 0.3%
Supply ChainCode ExecutionFrameworkModel
ficklingPatch: 0.1.6CWE-184625 ATLAS
CRITICALEXPLOIT AVAIL

cai-framework: Command Injection enables RCE

CVE-2025-67511
9.6
EPSS 2.0%
Code ExecutionPrompt InjectionAgentFramework
CWE-777 ATLAS
HIGHEXPLOIT AVAIL

n8n: security flaw enables exploitation

CVE-2025-65964
8.8
EPSS 0.7%
Code ExecutionSupply ChainAgentFramework
n8n166 ATLAS
MEDIUMEXPLOIT AVAIL

AI component: SQL Injection exposes database

CVE-2025-13922
6.5
EPSS 0.3%
Data ExtractionAuth BypassPluginAPI
5 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