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

96

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 1908 results — High severity
HIGHEXPLOIT AVAIL

OpenClaw Windows Node: env sanitizer bypass allows RCE

CVE-2026-101884
7.5
EPSS 0.5%
Code ExecutionAuth BypassAgentFrameworkPlugin
openclawCWE-18434 ATLAS
HIGHEXPLOIT AVAIL

OpenClaw Windows Node: weak exec approvals allow RCE

CVE-2026-101882
8.8
EPSS 0.7%
Code ExecutionAuth BypassAgentFrameworkPlugin
openclawCWE-18435 ATLAS
HIGHEXPLOIT AVAIL

OpenClaw Windows Node: approval bypass via pipe/subst

CVE-2026-101880
8.8
EPSS 0.7%
Auth BypassCode ExecutionAgentPluginFramework
openclawCWE-86334 ATLAS
HIGHEXPLOIT AVAIL

vLLM: Gemma4 parser flaw allows remote DoS

CVE-2026-103241
7.5
EPSS 0.7%
DoSInferenceFrameworkAPI
vllmCWE-404943 ATLAS
HIGH

rpm: heap overflow via crafted package hits RHOAI images

CVE-2026-103242
7.1
Code ExecutionDoSSupply ChainFramework
rhoai/odh-mlflow-operator-rhel96952 ATLAS
HIGH

JupyterLab: clipboard cell-paste trust bypass enables XSS

CVE-2026-102831
8.1
EPSS 0.2%
Code ExecutionData LeakageSocial EngineeringFramework
jupyterlite-corePatch: 0.8.4CWE-791.9K2 ATLAS
HIGH

Ollama: agent Bash approval bypass via shell operators

CVE-2026-102697
7.8
EPSS 0.1%
Code ExecutionAuth BypassPrompt InjectionAgentInferenceFramework
ollamaCWE-8631.9K4 ATLAS
HIGH

rpm: heap overflow parsing crafted RPM hits RHOAI images

CVE-2026-95520
7.1
Supply ChainDoSFramework
rhoai/odh-mlflow-operator-rhel96952 ATLAS
HIGHEXPLOIT AVAIL

LiteLLM: JWT email fallback enables admin account takeover

CVE-2026-93355
8.1
EPSS 0.3%
Auth BypassData LeakageAPIInferenceFramework
litellmCWE-139064 ATLAS
HIGH

GCC libstdc++: erase_if use-after-free causes DoS

CVE-2026-102010
7.0
DoSFrameworkInference
rhoai/odh-mlflow-operator-rhel96951 ATLAS
HIGH

Unsloth Zoo: code injection via model_type enables RCE

CVE-2026-93348
8.1
EPSS 0.4%
Code ExecutionSupply ChainFrameworkModelTraining Data
5 ATLAS
HIGH

code-ollama: shell injection in grep_search allows RCE

GHSA-456v-xq2p-r4cj
7.8
Code ExecutionPrompt InjectionSupply ChainAgentPluginInference
ollamaCWE-781.9K4 ATLAS
HIGHEXPLOIT AVAIL

aaPanel BaoTa: OS command injection in unzip handler

CVE-2026-101009
8.4
EPSS 1.8%
Code ExecutionFramework
CWE-772 ATLAS
HIGHEXPLOIT AVAIL

MONAI: unsafe pickle deserialization allows RCE

CVE-2026-100846
8.8
EPSS 0.4%
Code ExecutionSupply ChainFrameworkTraining Data
monaiCWE-5021284 ATLAS
HIGHEXPLOIT AVAIL

MONAI: unsafe pickle deserialization in NumpyReader RCE

CVE-2026-100845
7.8
EPSS 0.2%
Code ExecutionSupply ChainFrameworkTraining Data
monaiCWE-5021284 ATLAS
HIGHEXPLOIT AVAIL

MONAI: OS command injection via nnUNetV2Runner config

CVE-2026-100844
7.8
EPSS 0.9%
Code ExecutionSupply ChainFrameworkTraining Data
monaiCWE-781283 ATLAS
HIGHEXPLOIT AVAIL

MONAI: unsafe pickle deserialization enables RCE

CVE-2026-100843
7.8
EPSS 0.3%
Code ExecutionSupply ChainFrameworkTraining DataModel
monaiCWE-5021284 ATLAS
HIGHEXPLOIT AVAIL

MONAI: eval sandbox bypass allows code execution

CVE-2026-100842
8.8
EPSS 0.2%
Code ExecutionSupply ChainFrameworkModel
monaiCWE-951284 ATLAS
HIGH

MONAI: pickle cache deserialization allows local code execution

CVE-2026-100841
7.8
EPSS 0.1%
Code ExecutionSupply ChainFrameworkTraining Data
monaiCWE-5021284 ATLAS
HIGHEXPLOIT AVAIL

MONAI: code execution via malicious bundle config

CVE-2026-100840
7.8
EPSS 0.3%
Code ExecutionSupply ChainFrameworkModel
monaiCWE-951285 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