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 400 results — Medium severity, has patch
MEDIUM

n8n: editor-level access leaks credential headers

CVE-2026-59209
6.5
EPSS 0.3%
Auth Bypass Data Leakage Agent API
n8n Patch: 1.123.61 CWE-200 16 3 ATLAS
MEDIUM

Open WebUI: arena bypass reaches restricted models

CVE-2026-59225
5.4
EPSS 0.2%
Auth Bypass Model Inference
open-webui Patch: 0.10.0 CWE-862 4 3 ATLAS
MEDIUM

Open WebUI: IDOR lets read-only users write/delete files

CVE-2026-59212
5.4
EPSS 0.3%
Auth Bypass RAG Framework
open-webui Patch: 0.10.0 CWE-863 4 3 ATLAS
MEDIUM

Open WebUI: SSRF via web-fetch blocklist bypass

CVE-2026-59223
4.3
EPSS 0.2%
Auth Bypass Data Leakage RAG Plugin
open-webui Patch: 0.10.0 CWE-693 4 2 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: channel IDOR leaks tool-server API keys

CVE-2026-59222
--
EPSS 0.3%
Data Leakage Auth Bypass Privacy Violation Plugin Agent API
open-webui Patch: 0.10.0 CWE-200 4 3 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: read-only users can inject files into RAG KBs

CVE-2026-59217
4.3
EPSS 0.3%
Auth Bypass Prompt Injection RAG API
open-webui Patch: 0.10.0 CWE-862 4 2 ATLAS
MEDIUM

n8n: multi-issuer JWT sub collision bypasses auth

CVE-2026-59208
6.8
EPSS 0.3%
Auth Bypass Privacy Violation Agent
n8n Patch: 2.28.1 CWE-287 16 4 ATLAS
MEDIUM

n8n: MCP tool bypasses credential domain allowlist

CVE-2026-59207
6.5
EPSS 0.3%
Auth Bypass Data Leakage Agent Plugin
n8n Patch: 2.28.1 CWE-693 16 3 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: ReDoS in skill mentions blocks event loop

CVE-2026-59220
6.5
EPSS 0.4%
DoS Framework Plugin
open-webui Patch: 0.10.0 CWE-1333 4 2 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: image-edit API bypasses admin permission gate

CVE-2026-59227
4.3
EPSS 0.3%
Auth Bypass API Plugin
open-webui Patch: 0.10.0 CWE-862 4 3 ATLAS
MEDIUM

Open WebUI: timing leak enables account enumeration

CVE-2026-59218
5.3
EPSS 0.2%
Privacy Violation Auth Bypass Framework
open-webui Patch: 0.10.0 CWE-208 4 1 ATLAS
MEDIUM

LiteLLM: Zip Slip in Skills upload allows file write

CVE-2026-59820
6.5
EPSS 0.3%
Code Execution API Plugin
litellm Patch: 1.83.7 CWE-22 6 3 ATLAS
MEDIUM

LiteLLM: admin-scope local file read via OIDC ref

CVE-2026-59819
4.9
EPSS 0.3%
Data Leakage Data Extraction API Framework
litellm Patch: 1.83.10 CWE-73 6 2 ATLAS
MEDIUM

n8n: auth bypass moves workflows across project folders

CVE-2026-59253
5.0
EPSS 0.2%
Auth Bypass Agent
n8n Patch: 2.28.0 CWE-639 16 1 ATLAS
MEDIUM

Open WebUI: Stored XSS via HTML upload enables admin RCE

CVE-2025-46571
--
EPSS 0.3%
Code Execution Social Engineering Data Leakage Framework
open-webui Patch: 0.6.6 CWE-79 4 3 ATLAS
MEDIUM EXPLOIT AVAIL

onnx: crafted model triggers SIGSEGV in version_converter

CVE-2026-44512
5.5
EPSS 0.2%
DoS Supply Chain Model Framework
onnx Patch: 1.22.0 CWE-476 1.1K 3 ATLAS
MEDIUM

vLLM: malformed prompt embeds crash serving via M-RoPE

CVE-2026-55514
6.5
EPSS 0.4%
DoS Inference Model
vllm Patch: 0.24.0 CWE-617 130 3 ATLAS
MEDIUM EXPLOIT AVAIL

Coder: CORS bypass via workspace subdomain proxy

CVE-2026-55438
5.8
EPSS 0.1%
Auth Bypass Data Leakage Training Data API
github.com/coder/coder/v2 Patch: 2.34.2 CWE-346 6.2K 2 ATLAS
MEDIUM

Coder: stored XSS in agent logs risks admin session

CVE-2026-55437
5.4
EPSS 0.2%
Social Engineering Data Leakage Agent
github.com/coder/coder/v2 Patch: 2.34.2 CWE-79 6.2K 2 ATLAS
MEDIUM

Coder AI Bridge: suspended user auth bypass

CVE-2026-55435
5.4
EPSS 0.2%
Auth Bypass API Agent
github.com/coder/coder/v2 Patch: 2.34.2 CWE-863 6.2K 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