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 4307 results
HIGHKEVSCANNER

langflow: security flaw enables exploitation

CVE-2026-0770
--
EPSS 62.6%
Code ExecutionAuth BypassFrameworkAgent
langflowCWE-8295 ATLAS
UNKNOWNEXPLOIT AVAIL

langflow: Code Injection enables RCE

CVE-2026-0769
--
EPSS 41.2%
Code ExecutionAuth BypassData ExtractionFrameworkAgentPlugin
langflowCWE-957 ATLAS
UNKNOWNEXPLOIT AVAILSCANNER

langflow: Code Injection enables RCE

CVE-2026-0768
--
EPSS 28.1%
Code ExecutionAuth BypassFrameworkAgent
langflowCWE-946 ATLAS
UNKNOWN

Ollama: Command Injection enables RCE

CVE-2025-15063
--
EPSS 1.9%
Code ExecutionAuth BypassAgentPluginInference
CWE-786 ATLAS
HIGHEXPLOIT AVAIL

typebot: XSS enables session hijacking

CVE-2025-65098
7.4
EPSS 0.3%
Data ExtractionAuth BypassData LeakageAPIFrameworkAgent
CWE-799 ATLAS
CRITICAL

vllm: Code Injection enables RCE

CVE-2026-22807
9.8
EPSS 1.0%
Supply ChainCode ExecutionFrameworkInferenceModel
vllmCWE-94947 ATLAS
HIGH

claude_code: Weak Credentials allow account compromise

CVE-2026-21852
7.5
EPSS 27.5%
Supply ChainData ExtractionData LeakageAgentAPIFramework
claude_codeCWE-5226.3K6 ATLAS
HIGHEXPLOIT AVAIL

ollama: Input Validation flaw enables exploitation

CVE-2025-66960
7.5
EPSS 0.4%
DoSInferenceFrameworkModel
ollama1.9K5 ATLAS
HIGHEXPLOIT AVAIL

ollama: Input Validation flaw enables exploitation

CVE-2025-66959
7.5
EPSS 5.3%
DoSInferenceFramework
ollama1.9K3 ATLAS
HIGH

NVIDIA: Code Injection enables RCE

CVE-2025-33233
7.8
EPSS 0.2%
Code ExecutionAuth BypassSupply ChainFrameworkTraining DataModel
CWE-947 ATLAS
HIGHEXPLOIT AVAIL

chainlit: SSRF allows internal network access

CVE-2026-22219
7.7
EPSS 5.2%
Data ExtractionPrivacy ViolationFrameworkAPI
chainlitPatch: 2.9.4CWE-918415 ATLAS
HIGHEXPLOIT AVAIL

Chainlit: arbitrary file read via project/element

CVE-2026-22218
--
EPSS 9.7%
Data LeakagePrivacy ViolationFramework
Chainlit414 ATLAS
CRITICALEXPLOIT AVAIL

n8n: Code Injection enables RCE

CVE-2026-0863
9.9
EPSS 9.3%
Code ExecutionAuth BypassData ExtractionAgentFrameworkPlugin
n8nCWE-94168 ATLAS
HIGHEXPLOIT AVAIL

Thecus NAS: authenticated command injection to RCE

CVE-2021-47816
8.8
EPSS 1.8%
Code ExecutionTraining Data
Thecus N4800Eco Nas Server Control Panel5141 ATLAS
HIGH

keras: Resource Exhaustion enables DoS

CVE-2026-0897
7.6
EPSS 0.3%
DoSSupply ChainFrameworkModel
kerasPatch: 3.12.1CWE-7704.1K4 ATLAS
MEDIUM

libxml2: infinite catalog recursion crashes apps (DoS)

CVE-2026-0990
5.9
DoSSupply ChainFrameworkInference
rhoai/odh-mlflow-operator-rhel96952 ATLAS
MEDIUMEXPLOIT AVAIL

chainlit: IDOR enables unauthorized data access

CVE-2025-68492
4.2
EPSS 0.2%
Auth BypassData LeakageFrameworkAgent
chainlitPatch: 2.8.5CWE-639417 ATLAS
MEDIUM

n8n: security flaw enables exploitation

CVE-2025-68949
5.3
EPSS 0.3%
Auth BypassCode ExecutionAgentFramework
n8nCWE-134164 ATLAS
HIGHEXPLOIT AVAIL

ollama: security flaw enables exploitation

CVE-2025-15514
7.5
EPSS 0.8%
DoSInferenceAPIFramework
ollamaCWE-3951.9K4 ATLAS
HIGHEXPLOIT AVAIL

langchain: security flaw enables exploitation

CVE-2024-58340
7.5
EPSS 0.5%
DoSPrompt InjectionFrameworkAgent
langchainCWE-13333.2K8 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