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

344

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 535 results — Medium severity, no patch
MEDIUM

Zephyr RTOS: ext2 OOB read/DoS via malformed filesystem

CVE-2026-10645
4.9
DoS Data Extraction Inference
2 ATLAS
MEDIUM

Filament: auth bypass via Livewire state tampering

CVE-2026-48067
6.5
Auth Bypass Framework
CWE-639 2 ATLAS
MEDIUM

Filament: stored XSS in ImageColumn/ImageEntry

CVE-2026-48167
6.4
Data Extraction Code Execution Auth Bypass Framework
CWE-79 3 ATLAS
MEDIUM

Filament: unauth file upload drains disk/inflates costs

CVE-2026-48500
6.5
DoS Auth Bypass Framework
CWE-862 4 ATLAS
MEDIUM

Filament: timing side-channel exposes registered emails

CVE-2026-48166
5.3
Privacy Violation Auth Bypass Framework
CWE-208 3 ATLAS
MEDIUM

n8n: webhook forgery enables unauthorized workflow execution

CVE-2026-56357
4.0
Auth Bypass Code Execution Agent Plugin
n8n CWE-290 4 ATLAS
MEDIUM

LangChain: path traversal exposes files outside agent root

CVE-2026-55443
5.1
Prompt Injection Data Extraction Auth Bypass Framework Agent
langchain CWE-22 2.7K 5 ATLAS
MEDIUM

Langflow: code injection via Bundle URL Loader (PoC)

CVE-2026-12822
5.3
Code Execution Data Extraction Framework Agent
langflow CWE-74 4 ATLAS
MEDIUM

Flowise: path traversal in S3 loader exposes documents

CVE-2026-12821
6.3
Data Extraction Data Leakage Agent RAG Framework
Flowise CWE-22 5 ATLAS
MEDIUM

Craft CMS: stored XSS hijacks admin panel sessions

CVE-2026-56393
4.8
Code Execution Data Extraction Auth Bypass Framework Plugin
4 ATLAS
MEDIUM

litellm: authorization bypass exposes user list

CVE-2026-12799
4.3
Auth Bypass Data Extraction API Inference
litellm CWE-266 6 4 ATLAS
MEDIUM

litellm: SSRF in MCP OpenAPI spec loader endpoint

CVE-2026-12798
6.3
Data Extraction Auth Bypass Supply Chain Inference Agent Plugin
litellm CWE-918 6 4 ATLAS
MEDIUM

litellm: auth bypass in banned keywords enterprise hook

CVE-2026-12797
6.3
Auth Bypass Prompt Injection Inference API Framework
litellm CWE-285 6 4 ATLAS
MEDIUM

litellm: SSO session expiration allows auth persistence

CVE-2026-12796
6.3
Auth Bypass Data Extraction Inference API
litellm CWE-613 6 4 ATLAS
MEDIUM

litellm: SSRF in MCP server exposes cloud metadata

CVE-2026-12774
6.3
Auth Bypass Data Extraction Code Execution Inference API Agent
litellm CWE-918 6 5 ATLAS
MEDIUM

litellm: session expiration bypass in proxy auth

CVE-2026-12772
6.3
Auth Bypass Data Extraction Inference API
litellm CWE-613 6 5 ATLAS
MEDIUM

litellm: JWT auth bypass in M2M proxy handler

CVE-2026-12771
5.0
Auth Bypass Inference API
litellm CWE-266 6 5 ATLAS
MEDIUM

litellm: auth bypass in Admin Key Handler endpoint

CVE-2026-12770
5.4
Auth Bypass DoS Inference API
litellm CWE-266 6 4 ATLAS
MEDIUM

vLLM: ReDoS via crafted API input causes DoS

CVE-2025-71379
4.3
DoS Inference API
vllm CWE-1333 130 4 ATLAS
MEDIUM

picklescan: FileHandler bypass creates filesystem artifacts

CVE-2026-56304
6.5
Supply Chain DoS Framework Model
picklescan CWE-502 3 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