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
3,018

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

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 1382 results — Active exploitation
HIGH EXPLOIT AVAIL

picklescan: scanner bypass lets malicious pickle files evade detection

CVE-2025-71343
8.1
EPSS 0.3%
Supply Chain Code Execution Model Framework
picklescan CWE-502 3 4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: idlelib bypass hides pickle RCE

CVE-2025-71342
8.1
EPSS 0.4%
Supply Chain Code Execution Model Inference
picklescan CWE-502 3 4 ATLAS
CRITICAL EXPLOIT AVAIL

Keras: safe_mode=None bypass enables Lambda RCE

CVE-2026-12481
9.8
EPSS 0.5%
Code Execution Supply Chain Framework Model
keras Patch: 3.12.3 CWE-502 1.5K 4 ATLAS
HIGH EXPLOIT AVAIL

Langroid: path traversal escapes sandboxed file tools

CVE-2026-50181
7.1
EPSS 0.2%
Auth Bypass Data Leakage Agent Framework
langroid Patch: 0.64.0 CWE-22 4 4 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: IDOR cross-tenant data pollution

CVE-2026-58653
4.3
EPSS 0.2%
Auth Bypass Agent API
praisonai 1 2 ATLAS
UNKNOWN EXPLOIT AVAIL

MLflow: auth bypass allows cross-experiment trace access

CVE-2026-8147
--
EPSS 0.4%
Auth Bypass Data Leakage Framework API
mlflow/mlflow 674 2 ATLAS
HIGH EXPLOIT AVAIL

Gradio: path traversal in FileExplorer leaks files

CVE-2026-49119
7.5
EPSS 0.7%
Data Leakage Privacy Violation Framework
gradio CWE-22 669 3 ATLAS
HIGH EXPLOIT AVAIL

Ray: RCE via pickle/torch deserialization in WebDataset

CVE-2026-57516
8.8
EPSS 0.6%
Supply Chain Code Execution Training Data Framework
ray Patch: 2.56.0 CWE-502 619 4 ATLAS
MEDIUM EXPLOIT AVAIL

Keras: incomplete fix reopens HDF5 arbitrary file read

CVE-2026-12480
5.5
EPSS 0.1%
Data Leakage Supply Chain Privacy Violation Model Training Data
keras Patch: 3.12.3 CWE-73 1.5K 4 ATLAS
UNKNOWN EXPLOIT AVAIL

ClearML: path traversal in zip extraction enables RCE

CVE-2026-8387
--
EPSS 0.4%
Code Execution Supply Chain Framework Training Data Model
allegroai/clearml 25 5 ATLAS
HIGH EXPLOIT AVAIL

picklescan: scanner bypass enables pickle RCE

CVE-2025-71374
8.1
EPSS 0.6%
Supply Chain Code Execution Model
picklescan CWE-502 3 4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: malicious pickle bypasses RCE scan

CVE-2025-71371
8.1
EPSS 0.5%
Code Execution Supply Chain Model
picklescan CWE-502 3 4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: scan bypass lets malicious pickles hit RCE

CVE-2025-71368
8.1
EPSS 0.8%
Supply Chain Code Execution Model
picklescan CWE-502 3 4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: scanner bypass enables pickle RCE

CVE-2025-71363
8.1
EPSS 0.6%
Supply Chain Code Execution Model Inference
picklescan CWE-502 3 4 ATLAS
UNKNOWN EXPLOIT AVAIL

Picklescan: NumPy gadget bypass enables pickle RCE

CVE-2025-71355
--
EPSS 0.6%
Supply Chain Code Execution Model Framework
picklescan CWE-184 3 5 ATLAS
HIGH EXPLOIT AVAIL

picklescan: RCE bypass via trace.Trace.runctx

CVE-2025-71352
8.1
EPSS 0.6%
Supply Chain Code Execution Model
picklescan CWE-693 3 4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: scanner bypass enables pickle RCE

CVE-2025-71350
8.1
EPSS 0.4%
Supply Chain Code Execution Model Training Data
torch CWE-502 24.2K 5 ATLAS
HIGH EXPLOIT AVAIL

picklescan: bypass allows undetected pickle RCE

CVE-2025-71349
8.1
EPSS 0.6%
Supply Chain Code Execution Model
picklescan CWE-502 3 4 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: SSRF in web retrieval hits internal services

CVE-2026-56399
5.0
EPSS 0.3%
Auth Bypass Code Execution Data Leakage RAG API
open-webui 4 3 ATLAS
CRITICAL EXPLOIT AVAIL

Langflow: auth bypass in MCP transport exposes projects

CVE-2026-7663
9.8
EPSS 0.3%
Auth Bypass Data Leakage Code Execution Framework Agent Plugin
langflow CWE-285 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