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
2,375

AI/ML CVEs Tracked

336

Critical

408

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 820 results — Active exploitation, no patch
AWAITING NVD EXPLOIT AVAIL

vLLM: unauthenticated OOM DoS via video frame parsing

CVE-2026-5497
--
EPSS 0.4%
DoS Inference API
vllm CWE-400 130 3 ATLAS
CRITICAL EXPLOIT AVAIL

Boxlite: OCI symlink traversal enables host RCE

CVE-2026-46703
9.6
EPSS 0.5%
Supply Chain Code Execution Agent Inference
boxlite CWE-22 5 ATLAS
MEDIUM EXPLOIT AVAIL

draw.io: stored XSS executes JS via crafted diagram file

CVE-2026-46642
6.1
EPSS 0.2%
Code Execution Data Extraction Framework
CWE-79 4 ATLAS
HIGH EXPLOIT AVAIL

Flowise: mass-assignment allows cross-workspace takeover

CVE-2026-46480
8.8
EPSS 0.3%
Auth Bypass Data Extraction Agent Framework
flowise 4 ATLAS
HIGH EXPLOIT AVAIL

Flowise: mass assignment cross-workspace takeover

CVE-2026-46479
8.8
EPSS 0.3%
Auth Bypass Data Extraction Framework Agent
flowise 3 ATLAS
HIGH EXPLOIT AVAIL

Flowise: mass-assignment enables workspace takeover

CVE-2026-46475
8.8
EPSS 0.3%
Auth Bypass Data Extraction Agent Framework
flowise 4 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: sandbox escape enables authenticated RCE

CVE-2026-46442
9.9
EPSS 0.6%
Code Execution Auth Bypass Agent Framework
flowise CWE-94 5 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: mass assignment breaks multi-tenant isolation

CVE-2026-46441
9.6
EPSS 0.2%
Auth Bypass Data Extraction Agent Framework
flowise 4 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: plaintext auth brute-force, no rate limit

CVE-2026-46440
9.1
EPSS 0.3%
Auth Bypass Data Extraction Agent Framework
flowise CWE-522 5 ATLAS
MEDIUM EXPLOIT AVAIL

OpenAI Atlas: XSS enables browser history exfiltration

CVE-2026-11326
--
EPSS 0.2%
Auth Bypass Data Extraction Privacy Violation Plugin API
5 ATLAS
HIGH EXPLOIT AVAIL

Milvus: weak hash allows RBAC grantee impersonation

CVE-2026-10814
7.0
EPSS 0.1%
Auth Bypass Data Extraction Privacy Violation RAG Framework
milvus CWE-327 7 4 ATLAS
LOW EXPLOIT AVAIL

LMCache: weak hash enables KV cache integrity bypass

CVE-2026-10813
3.6
EPSS 0.1%
Data Leakage DoS Inference
3 ATLAS
MEDIUM EXPLOIT AVAIL

Streamlit: weak hash enables cache integrity bypass

CVE-2026-10804
4.7
EPSS 0.1%
Supply Chain DoS Framework Inference
streamlit CWE-327 2.9K 3 ATLAS
LOW EXPLOIT AVAIL

MLflow: weak dataset hash allows integrity bypass

CVE-2026-10803
3.6
EPSS 0.1%
Supply Chain Model Poisoning Framework Training Data
mlflow CWE-327 655 3 ATLAS
LOW EXPLOIT AVAIL

ms-swift: weak hash enables image cache poisoning

CVE-2026-10801
3.6
EPSS 0.1%
Model Poisoning Supply Chain Training Data Framework
ms-swift CWE-327 4 3 ATLAS
LOW EXPLOIT AVAIL

Gradio: weak hash exposes audio cache to local users

CVE-2026-10783
2.5
EPSS 0.1%
Data Extraction Privacy Violation Framework Inference
gradio CWE-327 685 3 ATLAS
UNKNOWN EXPLOIT AVAIL

jupyter-server: CORS bypass enables arbitrary code execution

CVE-2026-6657
--
EPSS 0.1%
Auth Bypass Code Execution Framework
CWE-346 5 ATLAS
CRITICAL EXPLOIT AVAIL

transformers: trust_remote_code bypass enables RCE via model load

CVE-2026-5241
9.6
EPSS 0.4%
Supply Chain Code Execution Framework Model
transformers CWE-829 8.3K 5 ATLAS
HIGH EXPLOIT AVAIL

MLflow: AI Gateway leaks cloud credentials via env injection

CVE-2026-4035
7.7
EPSS 0.3%
Data Extraction Auth Bypass Code Execution Framework API Inference
mlflow CWE-201 655 5 ATLAS
HIGH EXPLOIT AVAIL

jupyter-server: path traversal exposes sibling dir files

CVE-2026-5422
8.1
EPSS 0.5%
Data Extraction Code Execution Framework Training Data
jupyter CWE-23 1.9K 4 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