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 325 results — Critical severity, Active exploitation
CRITICALEXPLOIT AVAIL

praisonaiagents: sandbox escape enables host RCE

CVE-2026-39888
10.0
EPSS 0.5%
Code ExecutionAuth BypassAgentFramework
praisonaiagentsPatch: 1.5.115CWE-657205 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: YAML deserialization enables unauthenticated RCE

CVE-2026-39890
9.8
EPSS 0.6%
Code ExecutionSupply ChainAgentFramework
praisonaiPatch: 4.5.115CWE-50215 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: path traversal exposes full filesystem via agent tools

CVE-2026-35615
--
EPSS 0.4%
Data ExtractionCode ExecutionAgentFramework
PraisonAIPatch: 1.5.113CWE-2215 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: path traversal enables arbitrary file write/RCE

CVE-2026-39305
9.0
EPSS 0.3%
Code ExecutionPrompt InjectionSupply ChainAgentFramework
PraisonAIPatch: 4.5.11315 ATLAS
CRITICALEXPLOIT AVAIL

Claude Code: OS command injection, credential theft

CVE-2026-35022
9.8
EPSS 0.6%
Code ExecutionData ExtractionSupply ChainAgentAPIFramework
CWE-788 ATLAS
CRITICALEXPLOIT AVAIL

Budibase: Unauthenticated RCE as root via webhook

CVE-2026-35216
9.1
EPSS 10.9%
Code ExecutionAuth BypassData ExtractionFrameworkAgent
CWE-788 ATLAS
CRITICALEXPLOIT AVAILSCANNER

MLflow: auth bypass in job API enables unauthenticated RCE

CVE-2026-0545
9.1
EPSS 4.4%
Auth BypassCode ExecutionDoSFrameworkTraining Data
mlflowCWE-3066955 ATLAS
CRITICALEXPLOIT AVAIL

praisonaiagents: sandbox bypass enables full host RCE

CVE-2026-34938
10.0
EPSS 13.4%
Code ExecutionPrompt InjectionSupply ChainAgentFrameworkPlugin
praisonaiagentsPatch: 1.5.90CWE-693207 ATLAS
CRITICALEXPLOIT AVAIL

MLflow: command injection via model_uri in mlserver mode

CVE-2026-0596
9.6
EPSS 1.4%
Code ExecutionSupply ChainFrameworkInference
mlflowPatch: 3.9.0CWE-786954 ATLAS1 incident
CRITICALEXPLOIT AVAIL

CrewAI: RCE via Docker fallback in CodeInterpreter

CVE-2026-2275
9.6
EPSS 0.5%
Code ExecutionAuth BypassAgentFrameworkPlugin
6 ATLAS1 incident
CRITICALEXPLOIT AVAIL

MLflow: RCE via unsanitized model dependency specs

CVE-2025-15379
10.0
EPSS 2.4%
Code ExecutionSupply ChainFramework
mlflowPatch: 3.8.1CWE-776954 ATLAS1 incident
CRITICALEXPLOIT AVAIL

MLflow: path traversal enables sandbox escape, file overwrite

CVE-2025-15036
9.6
EPSS 0.6%
Supply ChainCode ExecutionFramework
mlflowPatch: 3.9.0rc0CWE-296955 ATLAS
CRITICALEXPLOIT AVAIL

langflow: security flaw enables exploitation

CVE-2026-33475
9.1
EPSS 3.2%
Supply ChainCode ExecutionData ExtractionFrameworkAgent
langflowCWE-745 ATLAS
CRITICALEXPLOIT AVAIL

langflow: Path Traversal enables file access

CVE-2026-33309
9.9
EPSS 13.5%
Code ExecutionAuth BypassSupply ChainFrameworkAgentPlugin
langflowPatch: 1.9.0CWE-228 ATLAS
CRITICALKEVSCANNER

langflow: Code Injection enables RCE

CVE-2026-33017
9.8
EPSS 96.2%
Model PoisoningCode ExecutionFrameworkAgentAPI
langflowPatch: 1.9.0CWE-956 ATLAS
CRITICALEXPLOIT AVAIL

mlflow: Path Traversal enables file access

CVE-2025-15031
9.1
EPSS 0.8%
Supply ChainModel PoisoningCode ExecutionFrameworkModelTraining Data
mlflowPatch: 3.9.0rc0CWE-226956 ATLAS
CRITICALEXPLOIT AVAIL

onnx: Integrity Verification bypass enables tampering

CVE-2026-28500
9.1
EPSS 0.3%
Supply ChainModel PoisoningCode ExecutionFrameworkRAGAPI
onnxCWE-3451.1K10 ATLAS
CRITICALEXPLOIT AVAIL

OpenClaw: RCE via request-side prompt injection

CVE-2026-30741
9.8
EPSS 0.9%
Prompt InjectionCode ExecutionAgentFramework
openclaw35 ATLAS1 incident
CRITICALEXPLOIT AVAIL

mcp-atlassian: Path Traversal enables file access

CVE-2026-27825
9.1
EPSS 12.3%
Code ExecutionPrompt InjectionSupply ChainAgentPluginFramework
mcp-atlassianPatch: 0.17.0CWE-2226 ATLAS
CRITICALEXPLOIT AVAIL

vllm: SSRF allows internal network access

CVE-2026-25960
9.8
EPSS 0.6%
Data ExtractionData LeakageCode ExecutionInferenceRAGAgent
vllmCWE-918947 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