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
2,371

AI/ML CVEs Tracked

345

Critical

449

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 1025 results — High severity
HIGH

picklescan: scanner bypass enables undetected RCE

CVE-2025-71376
8.1
Supply Chain Code Execution Model Training Data Framework
picklescan CWE-502 3 4 ATLAS
HIGH

picklescan: scanner bypass enables arbitrary code execution

CVE-2025-71370
8.1
Supply Chain Code Execution Model Framework
picklescan CWE-502 3 5 ATLAS
HIGH

picklescan: detection bypass enables RCE via numpy.f2py

CVE-2025-71365
8.1
Supply Chain Code Execution Model Framework
picklescan CWE-502 3 5 ATLAS
HIGH

picklescan: scanner bypass enables undetected RCE via pickle

CVE-2025-71341
8.1
Code Execution Supply Chain Model Framework
picklescan CWE-502 3 4 ATLAS
HIGH

Flowise before 3.0.10 (affected versions 3.0.7 and earlier) contains an unverified email change vulnerability. An authenticated user can change the account...

CVE-2025-71337
8.3
Flowise
HIGH

Gogs: Stored XSS via .ipynb Markdown re-render bypass

CVE-2026-52798
8.9
Code Execution Data Extraction Supply Chain Framework API
gogs.io/gogs Patch: 0.14.3 CWE-79 3.0K 5 ATLAS
HIGH

Budibase: SSRF via DNS rebinding in automation steps

CVE-2026-54353
8.5
Auth Bypass Data Extraction Data Leakage Agent API
@budibase/backend-core Patch: 3.39.9 CWE-367 5 ATLAS
HIGH

vLLM: dependency confusion RCE backdoors container images

CVE-2026-54232
8.8
Supply Chain Code Execution Data Extraction Inference Framework
vllm CWE-427 130 5 ATLAS
HIGH

Budibase: account hijack via chat identity CSRF

CVE-2026-50132
7.3
EPSS 0.0%
Auth Bypass Social Engineering Data Extraction Agent API
CWE-284 5 ATLAS
HIGH

picklescan: scanner bypass enables RCE via pickle

CVE-2025-71358
8.1
Supply Chain Code Execution Model Framework
picklescan CWE-502 3 5 ATLAS
HIGH

picklescan: scanner bypass enables undetected pickle RCE

CVE-2025-71344
8.1
Supply Chain Code Execution Model Framework
picklescan CWE-502 3 5 ATLAS
HIGH

picklescan: scanner bypass enables arbitrary code execution

CVE-2025-71339
8.1
Code Execution Supply Chain Model Framework
picklescan CWE-502 3 5 ATLAS
HIGH

Filament: stored XSS in disabled RichEditor field

CVE-2026-55409
7.6
Auth Bypass Data Extraction Framework API
CWE-79 4 ATLAS
HIGH

Filament: MFA race condition enables recovery code reuse

CVE-2026-48505
7.4
Auth Bypass Privacy Violation Framework
CWE-362 3 ATLAS
HIGH

Flowise: cross-workspace chatflow config disclosure

CVE-2026-56268
7.7
Auth Bypass Data Extraction Data Leakage Agent Framework API
Flowise CWE-863 5 ATLAS
HIGH

WebSphere AS: JAX-WS auth bypass, unauthorized access

CVE-2026-10845
7.3
Auth Bypass Data Extraction API Inference
3 ATLAS
HIGH

Chainlit: session hijacking via WebSocket restoration

CVE-2026-56104
8.2
Auth Bypass Data Extraction Framework Agent
chainlit 40 5 ATLAS
HIGH

Grafana: stored XSS in geomap bypasses CVE-2023-0507 fix

CVE-2026-9029
7.3
Code Execution Data Leakage Auth Bypass Framework API
4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: detection bypass enables RCE via pickle files

CVE-2025-71378
8.1
Supply Chain Code Execution Model Framework
picklescan CWE-502 3 4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: detection bypass enables RCE via malicious models

CVE-2025-71357
8.1
Supply Chain Code Execution Model Framework
picklescan CWE-502 3 5 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