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 4307 results
MEDIUMEXPLOIT AVAIL

ExLlamaV2: heap overflow in safetensors loader

CVE-2026-110695
6.3
EPSS 0.4%
Supply ChainDoSCode ExecutionInferenceModelFramework
CWE-1194 ATLAS
MEDIUMEXPLOIT AVAIL

OpenClaw ClawScan: scanner path-skip bypass evades detection

CVE-2026-110689
5.3
EPSS 0.1%
Supply ChainCode ExecutionAgentPluginFramework
openclawCWE-69333 ATLAS
MEDIUM

SageMaker SDK: git clone error leaks repo credentials to logs

CVE-2026-110248
5.3
EPSS 0.5%
Data LeakageData ExtractionFrameworkTraining Data
sagemaker503 ATLAS
MEDIUMEXPLOIT AVAIL

DataEase: stored XSS via chart axis label tooltip

CVE-2026-102756
--
EPSS 0.4%
Code ExecutionData LeakageFramework
2 ATLAS
HIGH

Ludwig: tar symlink path traversal allows arbitrary file write

CVE-2026-104103
8.1
EPSS 0.5%
Supply ChainCode ExecutionFrameworkTraining Data
3 ATLAS
HIGHEXPLOIT AVAIL

Portkey Gateway: SSRF via custom host header

CVE-2026-110719
7.2
EPSS 0.4%
Data LeakageAuth BypassAPIInferenceFramework
CWE-9183 ATLAS
LOW

Gitea: notebook CSS class injection enables UI redress

CVE-2026-60008
3.5
EPSS 0.4%
Social EngineeringFramework
1 ATLAS
MEDIUM

OW2 ASM: crafted class file triggers 2GB allocation DoS

CVE-2026-110257
5.5
EPSS 0.2%
DoSFramework
2 ATLAS
HIGHEXPLOIT AVAIL

VNote: argument injection in external program launch

CVE-2026-86022
7.0
EPSS 0.2%
Code ExecutionPlugin
2 ATLAS
HIGH

Claude Code: unverified plugin SHA checkout enables code install

CVE-2026-86063
--
EPSS 0.2%
Supply ChainCode ExecutionSocial EngineeringAgentPluginFramework
claude-codeCWE-4944 ATLAS
HIGH

Mistral Vibe: bash gate bypass allows silent RCE

CVE-2026-109429
8.8
EPSS 0.6%
Code ExecutionAuth BypassPrompt InjectionAgentFramework
mistral-vibe4735 ATLAS
HIGH

Mistral Vibe: bash parsing bypass allows hidden commands

CVE-2026-109428
8.8
EPSS 0.5%
Code ExecutionAuth BypassPrompt InjectionAgentFramework
mistral-vibe4734 ATLAS
MEDIUM

JupyterLab: trust prompt race marks wrong document trusted

CVE-2026-102832
4.2
EPSS 0.1%
Auth BypassCode ExecutionFramework
jupyterlite-corePatch: 0.8.4CWE-3671.9K2 ATLAS
MEDIUMEXPLOIT AVAIL

sherpa-onnx: buffer overflow via unvalidated model metadata

CVE-2026-108954
6.3
EPSS 0.3%
Supply ChainCode ExecutionDoSInferenceModelFramework
sherpa-onnx1.1K4 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: terminal proxy privilege escalation

CVE-2026-109572
7.6
EPSS 0.3%
Auth BypassCode ExecutionFrameworkAPI
open-webui23 ATLAS
HIGHEXPLOIT AVAIL

Nginx UI: MCP config_add bypasses directive validation

CVE-2026-84317
8.8
EPSS 0.5%
Code ExecutionPrompt InjectionAuth BypassAgentPluginAPI
CWE-204 ATLAS
HIGHEXPLOIT AVAIL

EdgeEver: stored XSS via MCP names steals bridge token

CVE-2026-109557
8.7
EPSS 0.4%
Code ExecutionData LeakageAgentPlugin
CWE-793 ATLAS
MEDIUM

HoloViz Panel: open redirect via login next parameter

CVE-2024-58389
6.1
EPSS 0.3%
Auth BypassSocial EngineeringFramework
panelCWE-6015142 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: SSRF via LLM-controlled SearxNG URL

CVE-2026-57143
8.8
EPSS 0.3%
Prompt InjectionData ExtractionData LeakageAgentFrameworkPlugin
praisonaiagentsCWE-20205 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI agents: unauthenticated access to agent endpoints

CVE-2026-57118
9.8
EPSS 0.4%
Auth BypassData LeakageCode ExecutionAgentFrameworkAPI
praisonaiagentsCWE-306206 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