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
2,393

AI/ML CVEs Tracked

342

Critical

305

New This Week

18

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 1029 results — High severity
HIGH EXPLOIT AVAIL

Flowise: mass assignment breaks tenant isolation

CVE-2026-42862
--
EPSS 0.2%
Auth Bypass Data Extraction Agent Framework
flowise Patch: 3.1.2 CWE-284 4 ATLAS
HIGH EXPLOIT AVAIL

Flowise: mass assignment breaks multi-tenant isolation

CVE-2026-42861
--
EPSS 0.3%
Auth Bypass Data Extraction Agent Framework
flowise Patch: 3.1.2 CWE-284 4 ATLAS
HIGH EXPLOIT AVAIL

claude-code-cache-fix: hook path injection → RCE

CVE-2026-45136
--
EPSS 0.2%
Code Execution Supply Chain Agent Plugin
claude-code-cache-fix Patch: 3.5.2 CWE-78 5 ATLAS
HIGH

LangSmith: prompt deserialization enables SSRF + data leak

CVE-2026-45134
7.1
EPSS 0.2%
Supply Chain Data Extraction Data Leakage Framework Agent API
langchain Patch: 0.3.30 CWE-502 2.7K 5 ATLAS
HIGH EXPLOIT AVAIL

nnU-Net: prompt injection hijacks CI/CD triage agent

CVE-2026-44246
7.2
EPSS 0.2%
Prompt Injection Code Execution Agent Plugin
claude-code 5 ATLAS
HIGH

CosyVoice: RCE via unsafe torch.load() model deserialization

CVE-2026-31232
8.8
EPSS 0.5%
Supply Chain Code Execution Model Inference
5 ATLAS
HIGH

snorkel: RCE via unsafe model deserialization

CVE-2026-31224
8.8
EPSS 0.4%
Supply Chain Code Execution Model Framework
snorkel CWE-502 22.7K 4 ATLAS
HIGH

snorkel: RCE via insecure model checkpoint loading

CVE-2026-31222
8.8
EPSS 0.4%
Code Execution Supply Chain Model Training Data
snorkel CWE-502 22.7K 4 ATLAS
HIGH

pytorch-lightning: RCE via insecure checkpoint deserialization

CVE-2026-31221
7.8
EPSS 0.4%
Supply Chain Code Execution Framework Model
pytorch-lightning CWE-502 1.6K 4 ATLAS
HIGH EXPLOIT AVAIL

MLflow: path traversal allows unauthenticated file read

CVE-2026-2614
7.5
EPSS 0.7%
Auth Bypass Data Extraction Framework Training Data
mlflow Patch: 3.10.0 CWE-22 655 5 ATLAS
HIGH EXPLOIT AVAIL

MLflow: SSRF in webhook URL enables cloud credential theft

CVE-2026-2393
7.1
EPSS 0.3%
Data Extraction Auth Bypass Framework
mlflow Patch: 3.9.0 CWE-918 655 4 ATLAS
HIGH

flash-attention: RCE via unsafe checkpoint deserialization

CVE-2026-31253
7.3
EPSS 0.2%
Code Execution Supply Chain Framework Training Data
flash_attn CWE-94 22.7K 4 ATLAS
HIGH EXPLOIT AVAIL

BentoML: Dockerfile injection enables build-time RCE

CVE-2026-44346
8.8
EPSS 0.3%
Supply Chain Code Execution Framework Inference
bentoml Patch: 1.4.39 CWE-78 21 5 ATLAS
HIGH EXPLOIT AVAIL

BentoML: unsanitized base_image allows Dockerfile RCE

CVE-2026-44345
8.8
EPSS 0.3%
Supply Chain Code Execution Framework
bentoml Patch: 1.4.39 CWE-78 21 4 ATLAS
HIGH EXPLOIT AVAIL

open-webui: IDOR exposes cross-user AI memory data

CVE-2026-44570
8.3
EPSS 0.3%
Auth Bypass Data Extraction Privacy Violation API Agent
open-webui Patch: 0.6.19 CWE-639 5 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: IDOR enables cross-user message tampering

CVE-2026-44569
7.1
EPSS 0.3%
Auth Bypass API Framework
open-webui Patch: 0.6.19 CWE-862 4 ATLAS
HIGH EXPLOIT AVAIL

open-webui: path traversal enables file write/delete

CVE-2026-44565
8.1
EPSS 0.5%
Code Execution DoS Inference Framework
open-webui Patch: 0.6.10 CWE-22 5 ATLAS
HIGH

open-webui: CORS misconfiguration enables 1-click RCE

GHSA-6xcp-7mpr-m7wm
8.3
Code Execution Auth Bypass Framework Inference
open-webui Patch: 0.3.33 CWE-613 5 ATLAS 1 incident
HIGH

PraisonAI: tar symlink bypass allows arbitrary file write

CVE-2026-44340
7.5
EPSS 0.4%
Supply Chain Code Execution Agent Framework
PraisonAI Patch: 4.6.37 CWE-22 1 5 ATLAS 1 incident
HIGH EXPLOIT AVAIL

praisonaiagents: tool bypass enables undeclared callable exec

CVE-2026-44339
8.6
EPSS 0.4%
Code Execution Auth Bypass Agent Framework
PraisonAI Patch: 4.6.37 CWE-470 1 5 ATLAS 1 incident

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