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 1553 results — no patch
MEDIUM

Mercator: SSRF enables internal network RCE via gopher://

CVE-2026-49345
--
Code Execution Data Extraction API Inference
CWE-918 4 ATLAS
HIGH

agentic-flow: MCP tool args enable OS command injection RCE

GHSA-vcv2-r9jh-99m5
8.8
Code Execution Supply Chain Agent Plugin
CWE-78 5 ATLAS
HIGH

line-desktop-mcp: unauthenticated HTTP exposes LINE chats

CVE-2026-49357
--
Auth Bypass Data Extraction Privacy Violation Agent Plugin
CWE-306 6 ATLAS
MEDIUM

FFmpeg RASC: UAF in decoder crashes AI inference containers

CVE-2026-12706
6.5
DoS Supply Chain Inference Framework
rhoai/odh-vllm-gaudi-rhel9 130 3 ATLAS
CRITICAL

pgAdmin 4: Stored XSS enables full browser session hijack

CVE-2026-12048
9.3
Code Execution Data Extraction Social Engineering Framework RAG
4 ATLAS
HIGH

PraisonAI: path traversal → arbitrary file read/write/RCE

CVE-2026-56078
8.8
Code Execution Data Extraction Auth Bypass Agent Framework
PraisonAI CWE-22 1 6 ATLAS
MEDIUM

PraisonAI: agent ID collision leaks system prompts

CVE-2026-56077
6.5
Data Leakage Data Extraction Privacy Violation Agent Framework
PraisonAI CWE-668 1 5 ATLAS
HIGH

PraisonAI: CORS bypass enables arbitrary agent execution

CVE-2026-56076
8.1
Auth Bypass Data Extraction Code Execution Agent API Framework
PraisonAI CWE-942 1 6 ATLAS
HIGH

PraisonAI: RCE via hardcoded approval_mode bypass

CVE-2026-56075
8.8
Code Execution Auth Bypass Agent Framework
PraisonAI CWE-863 1 5 ATLAS
MEDIUM

PraisonAI: tool approval bypass enables credential theft

CVE-2026-56074
5.5
Auth Bypass Data Extraction Agent Plugin
PraisonAI CWE-863 1 5 ATLAS
AWAITING NVD

jupyter-server: stored XSS yields kernel RCE

CVE-2026-44727
--
Code Execution Data Extraction Auth Bypass Framework Inference
notebook CWE-79 3.0K 6 ATLAS
HIGH

PraisonAI: sandbox escape via silent Landlock fallback

GHSA-6jcq-6546-qrrw
8.8
Code Execution Data Extraction Auth Bypass Agent Framework
praisonaiagents CWE-668 11 5 ATLAS
HIGH

PraisonAI: workflow policy bypass enables shell RCE

GHSA-7qw2-w5rc-37x2
7.8
Auth Bypass Code Execution Agent Framework
praisonaiagents CWE-78 11 5 ATLAS
AWAITING NVD EXPLOIT AVAIL

picklescan: scanner bypass enables PyTorch RCE

CVE-2026-53875
--
EPSS 0.4%
Supply Chain Code Execution Model Framework
picklescan CWE-95 3 5 ATLAS
CRITICAL

picklescan: scanner bypass enables pickle RCE

CVE-2026-53874
9.8
EPSS 0.5%
Supply Chain Code Execution Model Framework
picklescan CWE-502 3 4 ATLAS
CRITICAL EXPLOIT AVAIL

picklescan: blocklist bypass allows arbitrary code exec

CVE-2026-53873
9.8
EPSS 0.5%
Supply Chain Code Execution Model Framework
picklescan 3 4 ATLAS
HIGH EXPLOIT AVAIL

picklescan: arbitrary file read bypasses RCE blocklist

CVE-2026-53872
7.5
EPSS 0.5%
Data Extraction Supply Chain Framework Model
picklescan 3 5 ATLAS
CRITICAL EXPLOIT AVAIL

picklescan: blocklist bypass enables full RCE

CVE-2026-3490
10.0
EPSS 0.6%
Supply Chain Code Execution Model Framework
picklescan CWE-183 3 5 ATLAS
CRITICAL EXPLOIT AVAIL

picklescan: scanner bypass enables RCE via model files

CVE-2025-71325
9.8
EPSS 0.5%
Supply Chain Code Execution Model Framework
picklescan 3 4 ATLAS
CRITICAL EXPLOIT AVAIL

picklescan: ctypes bypass enables full RCE via pickle files

CVE-2025-71323
9.8
EPSS 0.8%
Supply Chain Code Execution Framework Model
picklescan 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