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
3,019

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 859 results — High severity, no patch
HIGH EXPLOIT AVAIL

Gradio: SSRF via file_fetch() leaks cloud IAM creds

CVE-2026-59806
7.4
EPSS 0.2%
Data Leakage Social Engineering Framework API
gradio CWE-601 669 5 ATLAS
HIGH

n8n: workflow:read scope bypass triggers execution

CVE-2026-56776
7.4
EPSS 0.2%
Auth Bypass Code Execution Agent Plugin
n8n CWE-863 16 3 ATLAS
HIGH EXPLOIT AVAIL

OpenLLM: command injection via model repo name

CVE-2026-15035
7.8
EPSS 1.5%
Code Execution Inference Framework
2 ATLAS
HIGH

Foxit PDF: use-after-free in attachment panel via JS page deletion

CVE-2026-57252
7.8
EPSS 0.1%
Code Execution DoS Plugin
HIGH

better-auth: race condition mints duplicate OAuth tokens

CVE-2026-53518
8.1
EPSS 0.2%
Auth Bypass Data Leakage Agent API Framework
CWE-294 1 ATLAS
HIGH

Joomla: fallo de control de acceso en com_privacy

CVE-2026-48957
8.8
EPSS 0.2%
Auth Bypass Privacy Violation API
CWE-284
HIGH

AMP for WP: unsafe ZIP extraction enables file write

CVE-2026-6101
7.5
EPSS 0.6%
Code Execution Plugin
HIGH

vLLM: unbounded regex compile hangs inference worker (ReDoS)

CVE-2026-55574
7.5
EPSS 0.3%
DoS Inference
xgrammar CWE-1333 16 3 ATLAS
HIGH EXPLOIT AVAIL

fickling: denylist gaps let malicious pickles execute

CVE-2026-14534
8.8
EPSS 0.4%
Code Execution Supply Chain Framework Model
fickling 61 5 ATLAS
HIGH EXPLOIT AVAIL

HestiaCP: cronjob flaw lets low-priv users get root

CVE-2026-12196
--
EPSS 0.3%
Auth Bypass Code Execution Framework
1 ATLAS
HIGH

n8n: authenticated RCE via Execute Command node

CVE-2025-71380
8.8
EPSS 0.4%
Code Execution Auth Bypass Agent Plugin
n8n CWE-284 16 3 ATLAS
HIGH EXPLOIT AVAIL

picklescan: detection bypass enables pickle RCE

CVE-2025-71375
8.1
EPSS 0.4%
Supply Chain Code Execution Model Framework
picklescan CWE-502 3 4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: methodcaller bypass enables pickle RCE

CVE-2025-71373
8.1
EPSS 0.4%
Code Execution Supply Chain Model Framework
picklescan CWE-693 3 4 ATLAS
HIGH EXPLOIT AVAIL

Picklescan: RCE gadget bypasses pickle safety scanner

CVE-2025-71372
8.1
EPSS 0.4%
Supply Chain Code Execution Model
picklescan CWE-502 3 5 ATLAS
HIGH EXPLOIT AVAIL

picklescan misses malicious pickles via torch decoder

CVE-2025-71369
8.1
EPSS 0.4%
Supply Chain Code Execution Model Framework
picklescan CWE-502 3 4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: attrgetter bypass evades malicious pickle scan

CVE-2025-71367
8.1
EPSS 0.4%
Supply Chain Code Execution Model
picklescan CWE-502 3 4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: scan bypass lets malicious pickle RCE

CVE-2025-71366
8.1
EPSS 0.4%
Supply Chain Code Execution Model Framework
picklescan CWE-502 3 4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: scanner blind spot enables pickle RCE

CVE-2025-71364
8.1
EPSS 0.6%
Supply Chain Code Execution Model Framework
picklescan CWE-502 3 4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: scanner bypass enables RCE via numpy eval

CVE-2025-71362
8.1
EPSS 0.3%
Supply Chain Code Execution Model Framework
picklescan CWE-502 3 4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: scanner bypass enables pickle RCE

CVE-2025-71360
8.1
EPSS 0.3%
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