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 462 results — High severity, has patch
HIGH EXPLOIT AVAIL

Gitea: cached permission check allows repo takeover

CVE-2026-27775
8.8
EPSS 0.6%
Auth Bypass Supply Chain Training Data
code.gitea.io/gitea Patch: 1.26.3 CWE-863 6.3K 2 ATLAS
HIGH EXPLOIT AVAIL

Pillow: OOB read/DoS via unchecked mmap stride (McIdas)

CVE-2026-54058
--
EPSS 0.5%
Data Leakage DoS Inference Training Data Plugin
pillow Patch: 12.3.0 CWE-125 2 ATLAS
HIGH EXPLOIT AVAIL

Keras: unsafe pickle deserialization allows RCE

CVE-2026-12484
7.8
EPSS 0.2%
Code Execution Supply Chain Framework Model
keras Patch: 3.12.3 CWE-502 1.6K 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
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
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
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
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
HIGH EXPLOIT AVAIL

Open WebUI: session hijack enables cross-user code exec

CVE-2026-59216
7.7
EPSS 0.3%
Auth Bypass Code Execution Privacy Violation Agent Plugin
open-webui Patch: 0.10.0 CWE-94 4 4 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: revoked JWTs bypass WebSocket auth

CVE-2026-59219
7.1
EPSS 0.3%
Auth Bypass Data Leakage Framework API
open-webui Patch: 0.10.0 CWE-613 4 2 ATLAS
HIGH

n8n: prototype pollution lets guests hit admin APIs

CVE-2026-59206
7.1
EPSS 0.4%
Auth Bypass Privacy Violation Agent Framework API
n8n Patch: 1.123.61 CWE-1321 16 2 ATLAS
HIGH

Open WebUI: Pyodide sandbox bypass reaches admin RCE

CVE-2026-59214
7.3
EPSS 0.3%
Code Execution Auth Bypass Data Leakage Framework Agent Plugin
open-webui Patch: 0.10.0 CWE-79 4 3 ATLAS
HIGH EXPLOIT AVAIL

Serena: unauth dashboard API enables RCE via memory poisoning

CVE-2026-49471
8.3
EPSS 0.3%
Auth Bypass Prompt Injection Code Execution Agent API
serena-agent Patch: 1.5.2 CWE-306 6 ATLAS
HIGH

LiteLLM: MCP auth bypass via fabricated OAuth header

CVE-2026-59822
8.2
EPSS 0.3%
Auth Bypass API Agent Plugin
litellm Patch: 1.84.0 CWE-287 6 3 ATLAS
HIGH

LiteLLM: code exec via unsandboxed Custom Guardrails

CVE-2026-59821
7.2
EPSS 0.4%
Code Execution Data Leakage Framework API Plugin
litellm Patch: 1.82.0 CWE-94 6 3 ATLAS
HIGH

n8n: SQL injection via MySQL v1 node expressions

CVE-2026-59257
8.8
EPSS 0.3%
Code Execution Data Leakage Agent Plugin
n8n Patch: 1.123.61 CWE-89 16 3 ATLAS
HIGH

Open WebUI: stored XSS via chat 'embeds' iframe escape

CVE-2026-26193
7.3
EPSS 0.2%
Code Execution Auth Bypass Data Leakage Framework
open-webui Patch: 0.6.44 CWE-79 4 2 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