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
MEDIUMEXPLOIT AVAIL

llama-index-core: DoS causes service disruption

CVE-2025-6208
5.3
EPSS 0.4%
DoSFrameworkRAG
llama-index-corePatch: 0.12.41CWE-4001.3K4 ATLAS
HIGHEXPLOIT AVAIL

lollms: Access Control bypass enables privilege escalation

CVE-2026-1117
8.2
EPSS 0.6%
Auth BypassDoSAPIInferenceFramework
lollmsPatch: 2.1.0CWE-2844 ATLAS
HIGHEXPLOIT AVAIL

text-generation: DoS causes service disruption

CVE-2026-0599
7.5
EPSS 29.5%
DoSInferenceFrameworkAPI
text-generationPatch: 3.3.7CWE-4005 ATLAS
HIGHEXPLOIT AVAIL

mlflow: security flaw enables exploitation

CVE-2025-10279
7.0
EPSS 0.2%
Code ExecutionSupply ChainFrameworkTraining Data
mlflowPatch: 3.4.0rc0CWE-3796954 ATLAS
CRITICALEXPLOIT AVAIL

cai-framework: Command Injection enables RCE

CVE-2026-25130
9.7
EPSS 0.9%
Prompt InjectionCode ExecutionAgentFrameworkPlugin
CWE-789 ATLAS
LOW

llama-stack: security flaw enables exploitation

CVE-2026-25211
3.2
EPSS 0.2%
Data LeakageData ExtractionRAGFramework
llama-stackPatch: 0.4.4CWE-532144 ATLAS
HIGHEXPLOIT AVAIL

agpt: Code Injection enables RCE

CVE-2026-24780
8.8
EPSS 1.3%
Code ExecutionAuth BypassAgentFrameworkAPI
CWE-947 ATLAS
MEDIUM

Menu Panel: session fixation enables session hijacking

CVE-2025-7014
5.7
EPSS 0.3%
Auth BypassData ExtractionFramework
Menu Panel5143 ATLAS
MEDIUM

Menu Panel: IDOR auth bypass exposes confidential data

CVE-2025-7013
5.7
EPSS 0.4%
Auth BypassData ExtractionAPIFramework
Menu Panel5143 ATLAS
MEDIUM

agentos-taskweaver: Protection Bypass circumvents security controls

GHSA-gpx9-96j6-pp87
6.5
Prompt InjectionCode ExecutionAuth BypassAgentFrameworkPlugin
agentos-taskweaverCWE-6936 ATLAS
HIGHEXPLOIT AVAIL

vllm: SSRF allows internal network access

CVE-2026-24779
7.1
EPSS 0.6%
Auth BypassData ExtractionDoSInferenceFrameworkAPI
vllmCWE-918946 ATLAS
HIGHEXPLOIT AVAIL

pytorch: Code Injection enables RCE

CVE-2026-24747
8.8
EPSS 0.8%
Code ExecutionSupply ChainFrameworkModel
torchPatch: 2.10.0CWE-9426.1K6 ATLAS
MEDIUMEXPLOIT AVAIL

OpenSSL: OCB tail bytes left unencrypted in low-level API

CVE-2025-69418
4.0
EPSS 0.1%
Data LeakageFramework
CRITICALEXPLOIT AVAIL

n8n: Code Injection enables RCE

CVE-2026-1470
9.9
EPSS 20.4%
Code ExecutionAuth BypassData ExtractionAgentFrameworkPlugin
n8nCWE-95169 ATLAS
MEDIUM

GLib: Unicode case conversion overflow, OOB write

CVE-2026-1489
5.4
DoSCode ExecutionFrameworkInference
rhoai/odh-mlflow-operator-rhel96952 ATLAS
MEDIUM

GLib: Base64 integer overflow enables out-of-bounds write

CVE-2026-1484
4.2
DoSSupply ChainFrameworkInference
rhoai/odh-mlflow-operator-rhel96952 ATLAS
MEDIUMEXPLOIT AVAIL

bentoml: Path Traversal enables file access

CVE-2026-24123
6.5
EPSS 0.5%
Supply ChainData ExtractionFrameworkInference
bentomlCWE-22238 ATLAS
CRITICALEXPLOIT AVAIL

Kalrav: Arbitrary File Upload enables RCE

CVE-2025-13374
9.8
EPSS 1.1%
Code ExecutionAuth BypassData ExtractionPluginAgentAPI
CWE-4348 ATLAS
UNKNOWN

langflow: Deserialization enables RCE

CVE-2026-0772
--
EPSS 1.2%
Code ExecutionSupply ChainData ExtractionFrameworkAgentRAG
langflowCWE-5028 ATLAS
UNKNOWN

langflow: Code Injection enables RCE

CVE-2026-0771
--
EPSS 0.6%
Code ExecutionSupply ChainData ExtractionFrameworkAgentPlugin
langflowCWE-946 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