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
3,021

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 1076 results — has patch
MEDIUM

FiftyOne: wildcard CORS enables local file exfiltration

CVE-2026-53656
6.3
Data Extraction Auth Bypass Framework Training Data
fiftyone Patch: 1.17.0 CWE-346 3.0K 3 ATLAS
MEDIUM

n8n: permission bypass exposes external secrets

CVE-2026-59259
--
EPSS 0.3%
Auth Bypass Data Leakage Agent Framework
n8n Patch: 1.123.61 CWE-639 16 3 ATLAS
MEDIUM

n8n: authz bypass leaks external secrets

CVE-2026-59254
--
EPSS 0.3%
Data Leakage Auth Bypass Privacy Violation Agent API
n8n Patch: 2.28.1 CWE-639 16 2 ATLAS
MEDIUM

n8n-mcp: cross-tenant leak of workflow backups

CVE-2026-55608
4.2
EPSS 0.2%
Auth Bypass Data Leakage Agent Plugin
n8n-mcp Patch: 2.57.4 CWE-200 16 3 ATLAS
HIGH

yutu: arbitrary file write via MCP caption-download tool

CVE-2026-50158
7.7
Code Execution DoS Prompt Injection Agent Plugin
github.com/eat-pray-ai/yutu Patch: 0.10.9-dev1 CWE-73 620 4 ATLAS
CRITICAL

n8n-mcp: broken tenant isolation leaks workflow credentials

CVE-2026-54052
9.9
EPSS 0.2%
Auth Bypass Data Leakage Privacy Violation Agent Plugin
n8n-mcp Patch: 2.56.1 CWE-639 16 4 ATLAS
LOW EXPLOIT AVAIL

Keras: symlink bypass enables tar path traversal

CVE-2026-12482
3.1
EPSS 0.2%
Supply Chain Code Execution Framework Model
keras Patch: 3.12.3 CWE-22 1.6K 4 ATLAS
CRITICAL

DIRAC: SQLi chained into eval() gives RCE

CVE-2026-61667
9.9
Code Execution Data Extraction Training Data Framework
DIRAC Patch: 8.0.79 CWE-89 2.9K 4 ATLAS
HIGH

Decidim: JWT replay bypasses multi-tenant isolation

CVE-2026-45414
8.5
EPSS 0.3%
Auth Bypass Privacy Violation Data Leakage API Framework
decidim Patch: 0.31.5 CWE-287 499
HIGH

mcp-atlassian: path traversal leaks secrets via injection

GHSA-g5r6-gv6m-f5jv
7.7
Prompt Injection Data Leakage Agent Plugin
mcp-atlassian Patch: 0.22.0 CWE-22 5 ATLAS
HIGH

mcp-atlassian: path traversal leaks server files+creds

GHSA-wm45-qh3g-v83f
7.7
Data Extraction Data Leakage Agent Plugin
mcp-atlassian Patch: 0.22.0 CWE-22 4 ATLAS
HIGH

SiYuan: XSS in Bazaar README steals admin API token

CVE-2026-54070
7.1
EPSS 0.2%
Supply Chain Code Execution Plugin
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260628153353-2d5d72223df4 CWE-79 499 3 ATLAS
CRITICAL EXPLOIT AVAIL SCANNER

SiYuan Note: chrome-extension origin auth bypass

CVE-2026-54069
--
EPSS 0.6%
Auth Bypass Data Leakage Supply Chain Plugin API
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260628153353-2d5d72223df4 CWE-346 3.0K 3 ATLAS
HIGH EXPLOIT AVAIL SCANNER

SiYuan: /assets path traversal exposes API secrets

CVE-2026-54066
7.5
EPSS 1.9%
Auth Bypass Data Leakage Privacy Violation API Plugin
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260628153353-2d5d72223df4 CWE-22 3.0K 3 ATLAS
MEDIUM

mcp-atlassian: DNS-rebind bypass revives header SSRF

GHSA-489g-7rxv-6c8q
6.5
Auth Bypass Data Extraction Agent Plugin
mcp-atlassian Patch: 0.22.0 CWE-918 3 ATLAS
MEDIUM

n8n: disk exhaustion via data-table upload quota gap

CVE-2026-58661
4.3
EPSS 0.2%
DoS Agent
n8n Patch: 2.28.0 CWE-770 16 2 ATLAS
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
HIGH EXPLOIT AVAIL

Open WebUI: encoded path traversal in terminal proxy

CVE-2026-59221
7.7
EPSS 0.4%
Data Leakage Auth Bypass Framework Plugin
open-webui Patch: 0.10.0 CWE-22 4 2 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
HIGH

Open WebUI: terminal proxy allows user ID spoofing

CVE-2026-59224
8.0
EPSS 0.3%
Auth Bypass Code Execution Privacy Violation API Framework
open-webui Patch: 0.10.0 CWE-287 4 3 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